Overview

Object detection asks models to identify what objects are present and where they appear, usually by predicting labeled bounding boxes in images or video. Common approaches include fast one-stage CNN detectors such as YOLO, proposal-based Faster R-CNN, and end-to-end transformer detectors such as DETR; feature pyramids and attention help handle objects at different scales. Work also explores oriented and 3D detection, sensor fusion, open-vocabulary recognition, and learning with limited or changing labels, with COCO, VisDrone, DOTA, KITTI, and nuScenes among the benchmarks used. A central challenge is transferring strong benchmark results to small, occluded, or unfamiliar objects and real-world conditions while keeping models efficient and evaluations reliable despite incomplete annotations.

Latest papers

673 papers56 papers in the last four weeks, down 8% on the four weeks before. 0.4% of all new papers.

Nov 3, 2026

Impact of Input Resolution in Mammographic Mass Detection: A Controlled Multi-Architecture Study

Deep-learning-based mass detectors usually downsample mammograms, trading fine image detail for lower computational cost. However, published studies cannot reveal how much accuracy this trade-off sacrifices, since they also differ in architecture, preprocessing, and evaluation protocol. In this work, we isolated the effect of input resolution in a controlled study on the VinDr-Mammo dataset, training 18 detectors at six input resolutions ranging from 512 x 416 to 1600 x 1280 pixels, for 108 model-resolution combinations. Whole mammograms were resized without cropping or tiling. For each model, preprocessing, model initialization, augmentation, and evaluation procedures were kept fixed across resolutions. Detection accuracy was evaluated by mAP50 on the 219 mass-positive images of the official test split, and 57 combinations with test mAP50 of at least 0.60 were analyzed. From the lowest to the highest resolution, median mAP50 rose from 0.626 to 0.660 and the best mAP50 from 0.670 to 0.709. The best result, achieved by DINO with a ConvNeXt-S backbone, is the highest mAP50 reported to date on mass-positive VinDr-Mammo images. Gains were concentrated in small masses: for the smallest third of lesions, median mAP50 rose by 0.074 (from 0.367 to 0.441), compared with 0.007 and 0.032 for medium and large masses. Median training time increased from 0.45 to 1.40 h, and median inference time from 23.6 to 113.7 ms per image. Therefore, higher input resolution mainly benefits the small masses that are hardest to detect, at a computational cost that remains practical.
Nov 2, 2026

Camera Radar LiDAR Fusion via Point-Cloud Projection for Multi-Task Learning

Autonomous vehicles require robust perception systems to operate safely under diverse environmental conditions. While cameras provide high-resolution visual data, their performance significantly degrades in low-light and adverse weather. High Definition (HD) radar offers superior reliability and angular resolution under such conditions but lacks rich visual feature recognition. LiDAR, though expensive, delivers highly precise distance measurements and dense point clouds. Each sensor exhibits unique trade-offs, necessitating the development of advanced sensor fusion algorithms to harness complementary strengths while minimizing computational complexity and maintaining accuracy. In this study, the proposed fusion architecture performs early fusion by combining camera images with perspective-view point cloud data from HD radar and LiDAR sensors. The proposed model is trained to detect vehicles and segment free drivable space simultaneously. Experiments are performed on the RADIal dataset where we demonstrate that fusing point cloud data with camera images in front-view surpasses the performances of the most recent standalone and fusion models.
Nov 2, 2026

Geometric Refinement and Distributional Alignment for Sim2Real Roadside LiDAR Detection

We describe our approach to the LUMPI track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.4793 combined, from a detection mAP of 0.1333 and a realism score of 0.9126. Our contribution is not a new architecture. Working from a PointPillars baseline, we obtained most of our gains from three sources. First, a diagnosis that small object failure in roadside LiDAR is a localisation problem rather than a detection problem, which led to a parameter free geometric refinement worth 86 percent relative on pedestrian AP. Second, an audit of our own post processing which revealed that a shipped rule was destroying valid predictions, the repair of which produced our single largest detection gain at 335 percent relative on the Van class. Third, treating the realism metrics analytically rather than as a black box, which showed that one of the four components is a closed form function of nine summary statistics. We also report an experimental methodology that we believe is the more transferable result. Because mean AP decomposes into independent per class terms, a single submission can carry several mutually controlled experiments, and a submission assembled entirely from previously measured components has a score that is known before it is sent. We predicted our final score to four decimal places prior to submission. We report negative results at equal length, and give a full account of data provenance and compliance in Section 8, including a full account of every mechanism contributing to the submitted score.
Nov 2, 2026

Bg-Mix: On Using Image Backgrounds for Data Augmentation in Electron Microscopy Images

Electron microscopy (EM) serves as a cornerstone in virology enabling the visualization of viral particles and is widely used in research, diagnostics and morphological characterization of pathogens. Computer-assisted image analysis can help facilitate and speed up this labor-intensive method, however, typical EM virus datasets are small and sparsely labeled, resulting in a lack of readily available deep learning models due to training limitations. To overcome data shortages and leverage content-rich, diverse sample backgrounds, we employed background-based data augmentation. To this end, we propose Bg-Mix, a form of data augmentation method, which decomposes training images into foreground objects and backgrounds and subsequently rearranges both into novel augmented images. This not only enhances the performance of object detection models but also increases the diversity of the training data. Using Bg-Mix provides an increase between +0.8 and +3.3 box mean average precision (mAP) points over the baseline when tested across two datasets using two architectures, thereby demonstrating its effectiveness.
Nov 2, 2026

ILLRAW: Illumination-Aware RAW Object Detection

Existing RAW-based detectors typically introduce learnable ISP modules to convert RAW inputs into sRGB-like formats to fit off-the-shelf detectors. However, this RAW-to-sRGB paradigm decouples representation learning from the downstream detection task. Crucially, it forces the network to inherit human-centric visual priors while discarding intrinsic RAW advantages, such as linear sensor responses and high-bit-depth, minimally processed scene cues. In this paper, we propose ILLRAW, an ILLumination-aware end-to-end RAW object detection framework. Instead of reconstructing visually plausible sRGB images, ILLRAW directly learns detection-oriented RAW features through a lightweight feature adapter inserted at the input stage of existing detectors. ILLRAW estimates an illumination mask and introduces channel-sensitive embeddings to model Bayer-channel responses. These features are fused by an illumination attention fusion module. Experiments show clear improvements on the diverse AODRaw benchmark and competitive performance on LOD and PascalRAW, with particularly strong results under dark exposure.
Nov 2, 2026

TERA: Task-Evidence Restoration for Underwater Object Detection under Bandwidth-Constrained Transmission

Underwater object detectors are typically evaluated on pre-transmission images, overlooking additional degradation from bandwidth-constrained downscaling and compression. We introduce AquaTX, a controlled benchmark built from real underwater detection datasets with seen and held-out codecs. We also propose TERA, a metadata-blind receiver-side framework combining task-guided pixel restoration and dual-state feature correction while keeping the detector frozen. Under seen compound degradation, TERA improves mean average precision (mAP50:95, averaged over IoU thresholds from 0.50 to 0.95) from 37.7 to 50.0 on DUO-TX and from 31.5 to 41.3 on RUOD-TX relative to the frozen detector without restoration. TERA also preserves clean-input performance and remains competitive with detector fine-tuning under the held-out AVIF codec. These findings support transmission-aware evaluation and task-guided restoration for underwater object detection. Code is available at https://github.com/hijinkim/TERA.
Nov 2, 2026

Beyond Proposals: Region-Consistent Open-Set Object Detection

Open-set object detection (OSOD) suffers from a fundamental limitation under dense proposal mechanisms: highly overlapping proposals associated with the same object are often assigned contradictory known/unknown predictions. Existing methods perform open-set reasoning independently for each proposal, while ignoring the shared semantics among correlated proposals, resulting in fragmented detections and unstable open-set decisions. In this paper, we reformulate OSOD as an object-centric semantic inference problem, where correlated proposals jointly support a coherent region-level semantic decision. Based on this perspective, we propose OCSI-Net, a unified framework that combines object-centric semantic consistency with geometry-aware uncertainty stabilization. Specifically, OCSI-Net aggregates correlated proposals into structured region clusters and infers region-level semantics from aggregated semantic evidence, thereby enforcing coherent open-set predictions within the same object region. Furthermore, a geometry-aware uncertainty mechanism is introduced to stabilize optimization near open-set transition boundaries. Extensive experiments on multiple benchmarks demonstrate that OCSI-Net consistently achieves state-of-the-art performance, improving the harmonic mean of known and unknown detection by an average of 6.83% over the second-best method.
Nov 1, 2026

Resolve, Clear, or Defer: Training-Free Active Prototype Triage for Ecological Detection Pipelines

Ecological monitoring increasingly relies on camera traps and aerial surveys that generate large image collections. High-recall animal detectors can localize candidate animals at scale. However, they also produce many detections that still require expert review, including false positives, ambiguous cases, and animals difficult to identify at the species level. Since exhaustive review requires substantial effort, we propose training-free active prototype triage, where reviewed detections become reusable evidence to (1) Resolve supported foreground classes, (2) Clear likely background false positives, or (3) Defer insufficiently supported cases for expert review. Across camera-trap and aerial datasets, foreground recognition and false-positive rejection benefit from different pretrained representations: BioCLIP2 provides foreground evidence while DINOv3 provides background evidence, reducing erroneous foreground clearing while improving automatic foreground recovery. Deferring unsupported cases avoids the higher error rates caused by forced decisions. Compared with confidence-thresholded multiclass k-NN and uncertainty-sampling logistic regression, prototype triage improves foreground recovery while maintaining competitive or lower review burden. Acquisition goes beyond class discovery: even after classes are represented, prototype choice determines how reliably evidence propagates through the remaining detections. Our results suggest that once animal localization reaches high recall, the challenge shifts from finding animals to deciding which examples to review, how to reuse them, and when evidence does not support an automatic decision.
Oct 31, 2026

ROD-Dataset: A Pedestrian-Perspective Benchmark of Urban Obstacle Classes for YOLO-Based Detection

Two groups of pedestrians face avoidable risk on the city sidewalk: people living with visual impairment, who reach an obstacle before anything warns them, and people walking with divided attention, who register a hazard late or not at all. A vision system can warn them only about obstacles it has learned to recognize, so its training data limits the protection it offers. No suitable training set exists: public benchmarks are recorded from vehicles, aerial platforms, or fixed rigs, general-purpose detectors omit the street furniture that causes trips, and pedestrian-focused collections are confined to single regions with incompatible class schemes. This paper introduces the Real-time Obstacle Detection (ROD) dataset: more than 24,000 images and 40,000 annotated obstacles across 25 classes, from vehicles and people to the stairs, manholes, traffic cones, and benches that general-purpose detectors overlook. Because street furniture differs between cities, ROD unifies twenty-nine public collections onto one taxonomy and adds eye-level imagery from two contrasting cities on two continents, Tehran and Toronto. Every label is human-verified, and each capture campaign is admitted only after a compact detector shows it can learn the class. Six lightweight YOLO detectors (nano and tiny variants) benchmarked on ROD all exceed 0.86 recall; YOLO12n attains the highest recall (0.889), YOLO26n the highest precision (0.925), and YOLOv9t the best [email protected] (0.882) with the fewest parameters. Because the recall and mAP rankings disagree, selecting a model by mAP does not minimize missed obstacles, so per-class recall is reported for all 25 classes.
Oct 31, 2026

Smooth bounding box for object detection

Deep learning-based object detection models are highly dependent on the quality of annotated training data. However, large-scale datasets often contain inevitable label noise, with bounding box localization errors being a prevalent and impactful form in object detection. While label noise handling techniques are well-studied for image classification, their adaptation to the more complex problem of bounding box errors remains underexplored. To address this, we propose a novel Smooth Bounding Box (SBB) strategy to mitigate the adverse effects of bounding box annotation inaccuracies. Our key insight is that annotation errors are often linked to annotator factors rather than specific image content, allowing for a statistical correction approach. Based on object size distribution within datasets, we implement the SBB strategy through two methods: 1) Global Scaling Correction (GSC), which applies a uniform scaling factor to estimate and correct a global average error; and 2) Interval Scaling Correction (ISC), which categorizes objects by size into intervals and estimates a dedicated correction factor for each, enabling more precise, fine-grained calibration. For efficient optimization of multiple parameters in ISC, we design a tailored model fine-tuning strategy. Furthermore, we introduce a Normalized Residual Fluctuation (NRF) metric to quantitatively assess the smoothing effect and training stability. Extensive experiments on multiple benchmarks demonstrate that our method consistently enhances detection accuracy across various model architectures. Both GSC and ISC achieve significant performance improvements over strong baselines, including the latest YOLOv11n, without adding inference overhead. The codes are available at https://github.com/Acui001/SBB.git.
Oct 29, 2026

WebOverlay: High-Throughput Vision-Only Distillation for Extreme Aspect-Ratio Web Overlay Detection

Web overlays, such as cookie consent banners, newsletter prompts, and age gates, obstruct automated web crawlers and degrade downstream document representations. While proprietary multimodal Large Language Models (MLLMs) can accurately identify overlays, their latency and inference cost preclude web-scale ingestion. Conversely, lightweight vision models struggle with full-page renderings characterized by extreme vertical aspect ratios, where standard isotropic resizing collapses critical text features and causes false positives. In this work, we present WebOverlay, a high-throughput vision-only detector trained via distillation from a frontier vision-language teacher. We establish a dynamic tiling strategy that partitions extreme aspect-ratio web renders into aspect-preserving patches with spatial overlap, coupled with an aspect-ratio-aware boundary adjudication mechanism to eliminate boundary artifacts. To eliminate cross-modal latency overheads, our student model relies purely on visual cues, bypassing DOM tree parsing. WebOverlay significantly outperforms DOM-based heuristics and achieves competitive precision and recall against heavy proprietary MLLM baselines while delivering multiple orders of magnitude higher throughput and substantially reduced deployment costs.
Oct 29, 2026

ElasticFormer: Detecting Objects in HRW Shots via Elastic Computing Vision Transformer

Recent advances in gigapixel-level imaging have brought High-Resolution Wide shots to the forefront of research. However, these images present significant challenges: extreme sparsity of foreground, gigapixel-level resolutions and diverse target counts. This makes traditional close-up detectors inaccurate and slow as they are overwhelmed by the background. Although previous research has explored sparse backbones, their fixed sparsity patterns lack the adaptability required to handle diverse target numbers. To address this, we introduce ElasticFormer, a sparse backbone that dynamically allocates computational resources based on foreground proportion. After scoring windows based on variance, proposed ElasticSelector module will predict the foreground proportion for top-k selection. The mechanism guides the model to select target-containing windows, scaling resources in areas where objects are clustered. We introduce a novel loss function combined with the 3-phase training strategy for ElasticSelector, allowing it to function properly when bounding box annotations are missing. A WSOD study is carried on PASCAL VOC 2007 to evaluate its extensibility. Further, ElasticNet is created to verify its backbone-agnostic nature. In experiments on the PANDA gigapixel benchmark, ElasticFormer reduces backbone FLOPs by 80% while achieving a significant improvement in AP50 when compared to fixed-ratio sparse methods.
Oct 29, 2026

BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots

Recent advances in gigapixel-level imaging have brought High-Resolution Wide shots to the forefront of research. However, these images present significant challenges: extreme sparsity of foreground, gigapixel-level resolutions and interleaving of foreground and background. This causes traditional detectors and attention mechanisms to be hindered by background, resulting in inefficiency and inaccuracy. To tackle this problem, we propose BiHashFormer, a dual sparsified branch transformer built on hashing. RoI Selector will predict the foreground proportion for top-k selecting target-containing windows. The compression branch processes windows selected and refines attention into HashAttention by discarding half of the key-value pairs, reducing cost and improving efficiency. The compensation branch uses HashMiner to perform low-cost hash searches in the remaining regions, recovering features of missed objects. Experiments confirm that the selection relationship in HashAttention is one-way and reveal the preference of different queries for keys. In experiments on the gigapixel benchmark PANDA, BiHashFormer reduces 37.5% backbone FLOPs while improving AP50 to 81.0%. Moreover, this parallel dual-branch structure allows the model to avoid inference delays caused by inter-branch dependencies, while achieving much greater stability than single-branch models, specially with low rates of RoI selection.
Oct 29, 2026

NIF: Normal-Intersection Fields for Geometrically Consistent Oriented Box Refinement

Accurate oriented detection requires boxes to follow object boundaries, yet small errors in the coupled center, size, and angle estimates can displace long boundaries even when an object is correctly classified. We propose NIF, a plug-in refinement branch that represents box geometry with normal-intersection fields. Given a coarse oriented box, it samples local features at 20 boundary anchors and predicts signed distances along their outward normals. These observations have an exact affine representation in five rectangle parameters; a differentiable projection uses error-aware reliability weights to recover a geometrically consistent box. Tangential pooling preserves the normal-position profile, while the shared projection adds 0.132M parameters. On DOTA-v1.0, NIF obtains 77.98%, 79.03%, and 79.32% mAP with Oriented R-CNN, Strip R-CNN, and LSKNet-S, respectively; LSKNet-S gives the strongest single-scale result among the compared methods. NIF also reaches 68.19% mAP on DIOR-R and improves matched FAIR1M-v1.0 and DIOR-R baselines by 0.30% and 0.71%, respectively. On HRSC2016, it raises mean IoU from 0.867 to 0.888 while reducing field error by 24.5%. Finally, with four different detector frameworks frozen, NIF improves relative AP75 by 1.55-4.16% and COCO-style mAP by 0.37-3.76%, without detector retraining. Upon acceptance of this paper, we will publicly release the code at https://github.com/zsk466991125-collab/Normal-Intersection-Fields.
Oct 29, 2026

YOLOF-MLD: A Multi-Level Distillation Framework for Efficient Object Detection

Efficient object detection on resource-constrained edge devices is essential for safety-critical applications such as fire-smoke monitoring. However, current lightweight frameworks, such as YOLO26, still rely on the parameter-dense multi-branch Feature Pyramid Network (FPN), preventing full exploitation of their lightweight advantage. Replacing FPN with YOLOF's single-input-single-output (SiSo) neck is a promising solution but causes substantial accuracy loss. To alleviate this, we propose YOLOF-MLD, a CPU-efficient multi-level distillation (MLD) framework that combines a YOLO26n backbone, a SiSo neck, and MLD. It aligns features at the backbone via sliced-semantics matching, neck with receptive-field matching, and response levels. On D-Fire and Annotated Fire-Smoke (AFS) datasets, YOLOF-MLD reduces the parameter count of YOLO26n by 35.7% and achieves a 62.3% speedup on Raspberry Pi 5, attaining 71.6% and 59.9% mAP@50, respectively, compared with 75.5% and 60.0% for YOLO26n. These results demonstrate a competitive accuracy--latency trade-off for edge deployment. Our code is available at https://github.com/XiaolongWU111/YOLOF---MLD/blob/main/README.md.
Oct 28, 2026

TRIM: Temporal Run-Time Monitoring of 3D Object Detection via Activation Statistics

Reliable perception is essential to intelligent transportation systems, yet deep neural networks can silently miss safety-critical objects while continuing to produce apparently plausible outputs. Existing run-time monitors for 3D object detection generally assess each frame independently and therefore cannot exploit the temporal evolution of occlusion, point sparsity, and scene complexity. We present TRIM, a lightweight temporal monitor that detects missed-object failures without modifying or retraining the underlying detector. TRIM summarises intermediate activations using compact channel-wise statistics and processes short sequences of these summaries with a temporal convolutional network. Experiments on NuScenes show that temporal monitoring improves AUROC from 0.686 to 0.704 and reduces the false alarm rate at 95% recall from 0.818 to 0.759 compared with single-frame monitoring. Early and intermediate backbone features provide the strongest monitoring signal, while the temporal inference head requires only 0.159 ms on a CPU.
Oct 27, 2026

TriDifNet: A Unified Three-Task Diffusion Network for End-to-End RGB-T Perception

Infrared--visible (IR--VIS) multi-modal perception supports robust scene understanding under challenging illumination. Infrared and visible images are often misaligned due to platform motion, viewpoint changes, and modality-dependent distortions, causing registration errors to propagate into subsequent fusion and detection stages. We propose TriDifNet, a unified three-task diffusion network for end-to-end RGB-T perception. To the best of our knowledge, TriDifNet is the first diffusion-based network that jointly optimizes registration, fusion, and detection for misaligned RGB-T pedestrian perception. TriDifNet consists of three diffusion-based modules, i.e., the Registration Diffusion Module (RegDM), the Fusion Diffusion Module (FusDM), and the Detection Diffusion Module (DetDM). RegDM aligns the unaligned infrared image to the optical reference by estimating a dense deformation field. FusDM performs residual conditional diffusion to generate a detection-oriented fused representation with optical structural cues and complementary infrared saliency. DetDM formulates pedestrian detection as an iterative denoising process in bounding-box space. To couple the three tasks, TriDifNet introduces a closed-loop optimization mechanism, where detection semantics guide fusion and registration, and the fusion result further regularizes geometric alignment. A stage-wise progressive training strategy and a lightweight Nash multi-task learning (Nash-MTL)-based late-stage refinement are further adopted to balance registration, fusion, and detection optimization. Extensive experiments on the KAIST multispectral pedestrian benchmark show that TriDifNet achieves superior downstream detection performance under misaligned RGB-T settings. Against strong system-level competitors, TriDifNet achieves 65.44% Recall, 57.55% mAP50_{50}, and 26.83% mAP50:95_{50:95}.
Oct 26, 2026

OBB-PBD: Extending Parallel Box Decoding to Oriented Bounding Boxes for Referring Expression Grounding in Aerial Imagery

Referring expression grounding in overhead imagery requires oriented bounding boxes rather than horizontal ones, since aerial objects appear at arbitrary orientations. Most grounding models emit box coordinates sequentially; Parallel Box Decoding (PBD) instead predicts all geometry slots in one forward pass, but only for four-coordinate horizontal boxes. We extend this block-aligned interface to a six-slot oriented representation using a double-angle parameterization. Rather than assuming correctness from a decreasing loss curve, we verify the extension with image/prompt-shuffle controls and visibility/leakage probes, which show that the corrected model depends on both the image and the prompt rather than on prompt statistics alone. On the aerial vehicle visual grounding (AVVG) benchmark, whose targets are genuinely oriented, the extended model improves rotated intersection over union (rotIoU) from 0.1253 for the zero-shot baseline to 0.303 +/- 0.012 (mean +/- standard deviation over three training seeds) across the complete 6139-record test split spanning all 120 images. Learning oriented boxes rather than their axis-aligned envelopes adds 0.055 +/- 0.008 rotIoU beyond a matched control (per-seed 95% confidence intervals all excluding zero), whereas block expansion alone yields no rotIoU gain distinguishable from zero.
Oct 26, 2026

GIFT: Representation Geometry Matters for Single-Domain Generalized Object Detection

Single-Domain Generalized Object Detection (S-DGOD) aims to generalize from a single source domain to unseen domains under distribution shifts. Existing efforts mainly focus on simulating unseen domains or suppressing domain-specific factors. However, they largely overlook the intrinsic generalization capability embedded in Vision Foundation Models (VFMs). In this work, we show that unconstrained fine-tuning disrupts the geometric structure of pre-trained representations, which encodes domain-invariant semantics. Motivated by this, we propose Geometric-Invariance Fine-Tuning (GIFT), a geometric-aware fine-tuning method for VFMs. Specifically, we introduce a series of learnable Householder reflections to the pre-trained weights to encourage geometry-consistent adaptation under domain shift. In addition, we propose a lightweight channel-wise scaling to facilitate effective task-specific adaptation. Extensive experiments demonstrate that GIFT consistently outperforms state-of-the-art (SOTA) approaches on two S-DGOD benchmarks. Notably, by introducing fewer than 1% additional trainable parameters into the frozen backbone, the proposed method achieves improvements of +7.9% and +2.9% in mPC over the previous SOTA on the Cityscapes-C and Diverse Weather Dataset, respectively. This finding highlights that preserving representation geometry is crucial for robust cross-domain generalization, establishing GIFT as a principled and efficient solution to domain shift.
Oct 23, 2026

VERA-Hand: A Verified Multidimensional Benchmark for 2D Hand Pose Estimation in Third-Person Dynamic Gesture Videos

Hand landmarks serve as input for gesture recognition, sign language understanding, and touchless human-computer interaction. Yet hand pose estimators are typically evaluated with frame-wise localization metrics such as PCK or MPJPE, which are computed over matched predictions and overlook missed or spurious hands, handedness errors, and temporal instability. To address these limitations, we present VERA-Hand, a benchmark that evaluates estimators using manually verified, frame-level 2D annotations for 10,690 hands across four complementary dimensions (detection, localization, identification, and temporal stability), as well as a joint Pose-F1 metric that requires both correct detection and accurate localization. Evaluating six estimators spanning hand-specific, whole-body, reconstruction-based, and foundation-model paradigms, we find that no estimator dominates: rankings reorder sharply across dimensions. VERA-Hand also exposes failures that localization-only and downstream evaluations may not reveal, including cross-hand overlap in over 85% of frames for a recent foundation model. A post-hoc cleanup case study demonstrates how the benchmark can validate corrective interventions, while stratified analyses show that robustness varies across motion-blur classes and hand regions. We release the verified annotations, protocol, and code at https://gibranbenitez.github.io/VERA_Hand/
Oct 23, 2026

RootDown: Deploying and Benchmarking Models for Beet-Root Detection on Edge Devices

Quality inspection of sugar beets after harvest and storage is critical to preserve sugar content and ensure optimal processing efficiency. The transfer of harvested beets to field clamps or trucks provides an opportunity to visually inspect individual beets automatically on loader conveyors. However, this is a challenging task as the large number of beets causes partial overlap and occlusion, complicating both annotation and detection. In this work, we propose an end-to-end image-based pipeline for detecting partially occluded sugar beets in loading scenarios as a first step toward automated quality inspection. We introduce a dedicated benchmark and present an automatic annotation strategy that leverages the SAM 3 foundation model to generate bounding boxes. We compare models trained on manually annotated and automatically generated labels. Additionally, we investigate deployment considerations by benchmarking multiple inference configurations, including execution on an edge device, under realistic operational constraints regarding precision, inference time and power consumption. Our results show that, despite substantial occlusion and inherent annotation ambiguity, foundation-model-based labels can substitute for a substantial share of manual annotation, trading labeling effort for data volume at a modest accuracy cost. Furthermore, we demonstrate that a Raspberry Pi 5 equipped with a Hailo accelerator enables high-performance, low-power inference, making it a practical solution for mobile outdoor deployment.
Oct 22, 2026

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies object-level and pixel-level perception through structured next-token prediction. It supports multiple visual tasks including object detection, referring localization, counting, OCR, segmentation, and matting, enabling localization at any user-specific granularity, from points and boxes to masks and alpha mattes. Architecturally, we integrate a lightweight pixel decoder into the VLM via a special <OBJ> token to generate instance-level pixel outputs. We train the model with a three-stage curriculum SFT followed by mixed-task RL. Across over 30 benchmarks, WeVisOne-VL demonstrates leading performance on both object-level and pixel-level tasks, while maintaining robust rejection for object-absent queries. By releasing WeVisOne-VL to the open-source community, we hope to advance VLMs from broad visual understanding toward truly reliable perception systems for real-world deployment.
Oct 21, 2026

Open-Vocabulary Models and Label Propagation for Uncertainty-aware Pseudo-Labeling of Object Detection Datasets

Object detection models rely on large-scale annotated datasets that require substantial manual annotation effort. The labeling costs further increase when annotation uncertainty is captured through soft labels, as multiple annotations must be collected for each object. We address this challenge by introducing a semi-supervised framework for the uncertainty-aware annotation of object detection datasets. Our approach leverages open-vocabulary object detectors to generate region proposals and semantically meaningful object representations. Based on these representations, we construct an object-level similarity graph and propagate probabilistic label information. Our framework assigns soft labels to previously unlabeled objects, quantifying both aleatoric and epistemic uncertainty. We evaluate our method on four object detection benchmarks with soft-label annotations and demonstrate that high-quality annotations can be obtained with only a small fraction of manually labeled objects. Furthermore, we show that detectors trained on semi-automatically annotated data achieve performance comparable to models trained on fully manually annotated data. We achieve state-of-the-art downstream detection performance for the task of semi-supervised object detection on the COCO dataset, with 40.5% AP virtually matching the performance of the model trained on fully manually constructed data (40.9%) at only 1% of labeling costs. These results highlight the potential of open-vocabulary models and graph-based label propagation for efficient, accurate and uncertainty-aware pseudo-labeling.
Oct 21, 2026

FogTTA: Online Test-Time Adaptation for Robust Transformer-based Object Detection in Foggy Weather

Object detection models for autonomous driving commonly experience substantial performance drops when deployed under adverse weather due to the domain shift between training data and real-world operating conditions. This degradation is especially evident when models trained on clear-weather images encounter foggy environments with reduced visibility and contrast. To address this challenge, we introduce FogTTA, an online test-time adaptation framework designed to improve the robustness of Transformer-based object detectors in fog. Using RF-DETR as the underlying object detector, FogTTA enables real-time adaptation to the streaming target domain without requiring source data or retraining. The framework follows a teacher-student design, where the deployed model serves as the teacher and generates pseudo labels from weakly augmented target inputs. These predictions are subsequently refined through non-maximum suppression and confidence filtering. The student model then learns from strongly augmented target sample using the Varifocal loss to mitigate pseudo-label noise. The teacher is updated via exponential moving averaging to ensure stable and continuous adaptation. Experiments show that FogTTA outperforms prior baselines, delivering improved detection accuracy and stability while maintaining real-time performance.
Oct 21, 2026

RiO-DETRv2: Geometry-Aware Uncertainty Modeling Meets Real-Time Oriented Object Detection Transformer

RiO-DETR is the first real-time end-to-end transformer for oriented object detection, yet further localization gains require a more expressive box representation. Although distributional regression has succeeded in horizontal DETRs, extending it to oriented detection introduces geometry-misaligned boundary modeling and topology-inconsistent orientation refinement. We present RiO-DETRv2, a geometry-aware uncertainty modeling framework for real-time oriented object detection. To resolve the geometry mismatch, Object-Aligned Boundary Distribution Refinement represents box boundaries as probability distributions in an object-aligned coordinate system and progressively refines them across decoder layers. For better orientation topology consistency, we introduce Circular-to-Local Angular Residual Refinement that transitions from global periodic search to local fine-grained estimation. Unified OBB Quality-Aligned Learning further aligns classification, boundary and angular refinement with complete-OBB localization quality. Together, these designs improve localization without compromising efficiency, achieving a better balance between speed and accuracy. Specifically, RiO-DETRv2-l/x achieves 53.7/54.1 mAP50-95 on DOTA, outperforming RiO-DETR-l/x by 1.2/1.5 points with nearly unchanged computational cost. Code is available at https://github.com/RicePasteM/RiO-DETRv2.
Oct 20, 2026

A Process-Informed, Photorealistic Digital Twin for Vision-Based Inline Inspection of C-SMC Strip Deposition

Inline quality assurance for Sheet Molding Compound (SMC) manufacturing is hindered by the lack of large-scale, accurately labeled image datasets for training machine-learning models. This work presents a process-informed, photorealistic digital twin for carbon-fiber SMC strip deposition. A rigid-body simulation reproduces the deposition kinematics (settling, friction, belt motion), while a physically grounded polarization-rendering model produces realistic appearance, so that every image carries exact, mutually consistent labels in synchronized formats: oriented bounding boxes, point annotations, density maps, and polarization renderings (Angle and Degree of Linear Polarization). Because the joint distribution of many overlapping strips cannot be specified analytically, simulation yields exact, scalable ground truth that manual annotation cannot provide. The twin produces over 16,000 images across 3,300 frames, and the synthetic data replicate near-isotropic fiber orientation (axial concentration r < 0.05) consistent with as-deposited commercial SMC. Trained purely on synthetic data, YOLOv11 and CSRNet reach detection mAP50 up to 0.91, with a dedicated oriented-bounding-box detector confirming the oriented labels are directly trainable (mAP50 = 0.83); on real manufacturing images, the synthetic-to-real difference in edge and texture structure (Kolmogorov-Smirnov distance 0.46, distribution overlap 0.56) is of the same magnitude as the difference between two real acquisition series of the same material (0.41, overlap 0.57). The approach substantially reduces the labeling burden for camera-based inline inspection of fiber orientation and volume content.
Oct 20, 2026

SGLDet: Spectral-aware Global-Local Dynamic Modeling for Multispectral Aerial Object Detection

Multispectral aerial object detection aims to exploit spectral-spatial cues to address object detection challenges in complex aerial scenes. Existing methods mainly focus on spectral-spatial decoupling and object-aware spectral-spatial fusion to improve spectral utilization. However, two critical issues remain underexplored: 1) severe foreground-background imbalance caused by large scene coverage hinders reliable object recognition; 2) aerial objects exhibit substantial local variations in scale, orientation, and structure, which hinder accurate localization. To address these issues, we propose SGLDet, a spectral-aware global-local dynamic modeling framework for multispectral aerial object detection, which is motivated by the observation that object semantics are jointly determined by global spectral consistency and scene context, while precise localization requires dynamic feature modulation conditioned on the input spectral and spatial properties. To realize these properties, SGLDet consists of three coordinated components: a Spectral-driven Global Dynamic Modeling module that aggregates spectrally related features across the scene via similarity-guided sparse matching; a Multi-scale Global Context Integration module that constructs a compact scene memory for scene-guided contextual reasoning; and a Spectral-aware Input-dependent Calibration Aggregation module that performs expert-kernel aggregation with scene-guided spectral-spatial calibration to enable adaptive local feature modulation. Extensive experiments on MODA, HOD3K, and DroneVehicle demonstrate that SGLDet achieves superior performance with competitive computational cost. Code is available at https://github.com/Riiluo/SGLDet.
Oct 20, 2026

S3^3E-Det: A Strict Spatial-Spectral Equivariant Detector for Multispectral Object Detection

Multispectral object detection requires detectors to exploit material-dependent spectral responses while maintaining consistent localization under geometric variations. Existing MOD detectors learn discriminative spectral representations, yet lack a unified mechanism that preserves spectral order, adapts spectral-context fusion across pyramid levels, and regulates geometric responses under rotation. To address these limitations, we propose S3^3E-Det, a strict spatial-spectral equivariant detector that couples ordered spectral modeling with transformation-consistent prediction. Spectral Order-aware Sampling Calibration (SOSC) imposes local order constraints on input-derived spectral features through first-order variation, while Common-Differential Equivariant Fusion (CDEF) adapts spectral-context aggregation across pyramid levels. A compact Geometric Alignment Head (GAH) reconciles invariant and equivariant output properties within a unified prediction stage. Across MODA, HOD3K, and DroneVehicle, S3^3E-Det combines high detection accuracy with a compact parameter footprint and reduced rotation-induced variation. Code is available at https://github.com/Riiluo/S3E-Det.
Oct 20, 2026

Revealing Inter-Channel Modality Discriminability: Channel Selective Interaction Fusion Network for Optical-SAR Object Detection

Synthetic aperture radar (SAR) and optical imagery provide complementary structural and appearance information for remote sensing object detection. However, substantial cross-modal discrepancies and indiscriminate channel interaction inevitably introduce redundant or conflicting features. Since different feature channels encode heterogeneous semantic information and contribute unequally to cross-modal fusion, selectively highlighting task-relevant channels while suppressing redundant ones is essential. To address this issue, we propose the Channel Selective Interaction Fusion Network (CSIF-Net), which performs selective channel-level cross-modal interaction. CSIF-Net first employs a frequency decomposition module to construct frequency-aware SAR inputs, facilitating the separation of structural information from noise-related responses. It then models cross-modal channel relationships through a cross-attention channel selection module and dynamically partitions the features into shared and modality-specific components. Finally, a dual-branch fusion module performs cross-modal interaction and channel realignment for shared features while independently enhancing SAR-specific features, thereby exploiting complementary information and suppressing modality interference. Extensive experiments on the OGSOD 1.0 and M4-SAR datasets demonstrate that CSIF-Net achieves state-of-the-art performance in both horizontal and oriented object detection, surpassing the existing methods by 4.01% and 3.18% gains, respectively.
Oct 20, 2026

FocusOVD: Geometric and Contextual Feature Refinement for Open-Vocabulary Small-Object Detection

Open-vocabulary object detection aims to detect both seen and unseen categories by leveraging the semantic knowledge of vision-language models. However, existing methods often struggle with small objects due to insufficient preservation of high-resolution details, ineffective information aggregation across feature levels, and limited region-level discriminability. To address these challenges, we propose FocusOVD, an open-vocabulary object detector that enhances small-object representations without modifying the frozen VLM backbone. FocusOVD introduces three complementary components: a Reweighted Cross-scale Feature Fusion module, which learns normalized level-wise weights to adaptively balance shallow appearance details and deep semantic cues during feature pyramid aggregation; a Residual Pinwheel-shaped Gated Convolution module, which strengthens local geometric responses in high-resolution features; and a Residual Convolutional Gated Linear Unit module, which suppresses background-dominated activations and enhances RoI discriminability before prediction. Extensive experiments on COCO-OVD and LVIS-OVD demonstrate the effectiveness of FocusOVD. On COCO-OVD, FocusOVD achieves a novel-category AP of 36.3%, outperforming CORA, UniDetector, and SAMP by 1.3%, 1.1%, and 1.5%, respectively; on LVIS-OVD, it achieves an overall AP of 33.7%, surpassing the strongest competing method by 0.6%. These results demonstrate the strong generalization ability of FocusOVD for open-vocabulary small-object detection.