Overview

Multi-scale attention studies how models can combine fine-grained features with broader context across image regions, feature-pyramid levels, or time windows. Common approaches include hierarchical and window-based attention, cross-scale feature fusion, and efficient linear attention that allocates computation across resolutions. These methods are used in tasks such as object detection and segmentation on benchmarks like COCO and ADE20K, as well as time-series forecasting and sequence modeling. A central challenge is aligning useful information across scales while controlling computation, and gains must be tested across varied datasets and settings.

Latest papers

43 papers3 papers in the last four weeks, down 62% on the four weeks before. 0.0% of all new papers.

Nov 17, 2026

Where Global Context and Weight Sharing Work in Compact Vision Backbones

Compact convolutional backbones such as EfficientNet achieve strong parameter efficiency through local depthwise separable convolutions, yet two structural questions remain central to hybrid design: where does global self-attention improve recognition over pure convolution, and can repeated blocks share weights without losing representational capacity? We investigate both questions on ImageNet-1k (50,000-image validation) using controlled EfficientNet-B0 experiments. First, we show that wrapping a classification backbone in multi-scale feature pyramids (BiFPN) fails to outperform a plain MBConv trunk (69.99% - 71.81% vs. 72.86% plain B0) until paired with stage attention (73.15%). In contrast, keeping the MBConv trunk intact and inserting lightweight zero-gated residual self-attention adapters at stages P3 (28x28 windowed), P4 (14x14 global), and P5 (7x7 global) reaches 74.02% standalone and outperforms a bit-for-bit matched plain-B0 control by +0.954 percentage points (73.88% vs. 72.92%) across an 88-epoch stateless replay schedule, with learned attention amplitude rising monotonically with semantic depth (27.2% at P3 -> 45.4% at P4 -> 66.3% at P5). Second, we evaluate recurrent weight sharing across repeated MBConv blocks with pass-specific BatchNorm statistics (+1,536 parameters per pass). While post-hoc kernel averaging degrades accuracy to 17.03% and single-template stage tying (-27.6% parameters) plateaus at 66.10%, alternating two shared block templates ([B1, A, B, A]) in Stage 6 cuts total model parameters by 10.9% (582K weights) and recovers by +10.82 points in a single epoch to 70.92% (-1.84 points vs. unshared control).
Nov 5, 2026

Scale as a Modality: Multi-Scale Pixel-Space Diffusion Transformers

Latent diffusion models rely on pretrained autoencoders that introduce lossy compression and constrain spatial granularity. Pixel-space diffusion avoids this bottleneck and enables flexible tokenization at multiple spatial scales, yet existing approaches largely adopt two-level coarse-to-fine architectures with limited cross-scale interaction. We introduce MS-pDiT, a multi-scale pixel-space diffusion transformer that treats spatial scale as a modality. MS-pDiT tokenizes the same noisy image at multiple patch sizes, processes each scale in a dedicated transformer stream, and enables bidirectional information exchange through compacted MM-DiT-style joint attention, with attention cost independent of the finest patch size. This design establishes the number of scales as a new architectural scaling dimension. On ImageNet 256×256256\times256, increasing the number of scales from two to five consistently improves FID from 4.39 to 2.31, 2.26, and 2.19, while adding an intermediate scale substantially outperforms increasing depth under comparable parameter budgets. Further analysis highlights the importance of bidirectional cross-scale interaction and late introduction of fine-grained streams. MS-pDiT achieves FID scores of 1.43 and 1.44 on ImageNet 256×256256\times256 and 512×512512\times512, respectively, and naturally extends to text-to-image generation, achieving 0.86 on GenEval and 83.9 on DPG-Bench.
Oct 26, 2026

ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer

In the past few years, Vision Transformer (ViT) has achieved competitive performance in the field of computer vision. However, there still remain some problems. For instance, ViTs rely on large-scale training data since they simply contain a large number of trainable parameters, which slows down their learning efficiency and limits their applicability in resource-constrained scenarios. In this paper, we propose a novel deep learning model, namely All-Convolutional Self-Attention Network (ACSAN), which applies convolution operations to replace fully-connected matrices multiplications in the ViT framework. To implement ACSAN, we firstly design Dynamic Convolutional Self-Attention (DCSA) as the basic module, which employs multi-scale dilated convolutions to generate Query, Key, and Value. We define spatial self-attention and channel self-attention to generate attention features respectively. The two attention features are finally merged as the output of the DCSA module. Based on DCSA, we construct the basic ACSAN block. Specifically, we use DCSA to replace the regular self-attention operations, and use convolution-based Equivalent Convolutional Fully Connected (EqConvFC) modules to replace MLPs. To evaluate the performance, we train ACSAN on CIFAR-10, CIFAR-100 and ImageNet-1k datasets from scratch. Experimental results show that ACSAN achieves good classification accuracy (the best variants achieve 93.52% on CIFAR-10, 73.38% on CIFAR-100, and 83.3% on ImageNet-1k). Moreover, in comparison with standard ViT and other state-of-the-art methods, ACSAN uses fewer parameters to achieve comparable or better accuracy.
Oct 24, 2026

Cross-Scale Sparse Attention for Referring Segmentation in Remote Sensing

High-resolution remote sensing (RS) imagery provides fine spatial detail over large areas, making it essential for fine-grained scene understanding. Referring Remote Sensing Image Segmentation (RRSIS) aims to segment regions described by natural language, yet many existing methods rely on sequential alignment--fusion pipelines with limited joint modeling of cross-scale visual hierarchies and linguistic dependencies. Moreover, dense attention mechanisms struggle with the sparsity and wide spatial dispersion of RS targets, while current datasets offer limited structured evaluation of multi-target references, multi-hop relational reasoning, and multi-granularity descriptions, limiting both model development and evaluation. To address these challenges, we propose a Cross-Scale Sparse Attention Model (CSSAM), which aligns multiscale visual features with complex referring expressions through two key modules. The Cross-scale Modality-aligned Fusion Module (CMFM) performs unified cross-scale cross-modal fusion, while the Dynamic Multimodal Sparse Hybrid Attention (DMSHA) selectively attends to informative visual--textual tokens, reducing dense visual interactions. Furthermore, we introduce M3^{3}RRSIS-D, a RRSIS dataset explicitly designed around three core reasoning dimensions: multi-target (M1^{1}), reference-dependent multi-hop (M2^{2}), and multi-granularity (M3^{3}) expressions. Extensive experiments on M3^{3}RRSIS-D and two public RRSIS benchmarks demonstrate that CSSAM achieves competitive performance across accuracy, fine-grained reasoning, and high-IoU localization metrics, validating its effectiveness for complex semantic reasoning in realistic RS scenarios. Code, dataset, and model weights will be released upon acceptance.
Oct 15, 2026

DST-Net: Decomposed Spatio-Temporal Network for Time Series Forecasting

Series decomposition has emerged as a widely acknowledged paradigm in deep time series forecasting models. However, existing approaches predominantly employ a homogeneous modeling strategy for all subsequences, thereby overlooking the distinct inductive biases inherent in different components. We identify that the trend component exhibits dominant spatial coupling across channels but carries significant temporal redundancy, whereas the seasonal component is characterized by local temporal evolution but remains susceptible to attention distraction. To address this, we propose a novel disentangled architecture that tailors specific modeling strategies to align with the intrinsic properties of each component. For the trend branch, we design a Latent Graph Block, employing latent graph modeling to capture global topological dependencies and system-wide co-movements. Conversely, for the seasonal branch, we introduce a Gaussian Multi-scale Attention mechanism to mitigate attention distraction. By injecting learnable Gaussian priors, we impose structural constraints that compel the model to focus on multi-granular local contexts, effectively filtering out global noise and accurately capturing local evolutionary phases. Extensive experiments on multiple real-world benchmarks demonstrate the effectiveness of our proposed model.
Oct 13, 2026

MIST: Multi-Scale Spatial Context for Gene Expression Prediction from Histology

Predicting spatial gene expression from standard H&E images could extend molecular analysis to tissues without spatial transcriptomic measurements. A standard Transformer applies self-attention over spots but ignores where each spot sits in the tissue, whereas a spot's molecular state depends on tissue context at multiple spatial scales. Building on this insight, we introduce MIST, a Multi-context Spatial Transformer that augments the self-attention backbone with two context pathways applied in every layer: a coordinate-invariant local pathway that attends over spatial k-nearest-neighbor spots, and a slide pathway that broadcasts a whole-slide summary to every spot; the model predicts all spots in a single forward pass. Because coordinates enter only through pairwise distances, the local pathway is invariant to translations, rotations, and reflections when image features are fixed. In intra-cohort evaluation across six human organ cohorts from HEST-1k, MIST improves mean Pearson correlation over the strongest evaluated baseline by 9.7%, 11.6%, and 11.4% for 10-, 50-, and 100-gene panels, respectively, with the lowest average MSE and MAE. MIST further improves leave-one-organ-out transfer by 6.0% over the next strongest baseline, attains the best expression-derived domain recovery (highest mean ARI and NMI at every clustering resolution, and higher NMI than the closest baseline on 84% of held-out slides), and reproduces spatial expression patterns of selected cancer-marker genes. Together, these results show that adding local and slide context to a vanilla Transformer backbone is an effective approach to spatial gene expression prediction from histology.
Oct 7, 2026

SANet: Selective Attention Network for Infrared Small Target Detection

Infrared small target detection aims to accurately identify and locate dim targets in complex backgrounds and supports applications such as maritime surveillance and military search and rescue. However, the small size and weak contrast of infrared targets make it difficult to balance detection accuracy and false alarms. This paper proposes a selective attention network (SANet) for infrared small target detection. A dual-path semantic-aware module combines standard and pinwheel-shaped convolutions to preserve local spatial consistency and capture broader contextual information. Spatial and channel attention further refine the features and improve target-background discrimination. To address the limitations of static skip connections in U-Net, a selective attention fusion module adaptively integrates features across scales using spatially varying weights. It selectively enhances salient regions and improves discrimination between true targets and false alarms. Experiments on three public benchmarks, NUAA-SIRST, IRSTD-1K, and NUDT-SIRST, show that SANet achieves competitive performance in intersection over union (IoU), normalized IoU, detection probability, and false alarm rate. Its IoU exceeds that of the second-best method by 1.93, 4.32, and 2.21 percentage points, respectively. These results support the effectiveness of SANet in dim-target perception, discriminative feature representation, and background suppression.
Oct 7, 2026

Self-attention summary networks for subsurface velocity-model building from common-image gathers

Common-image gathers (CIGs) contain physically meaningful information about velocity-model errors through reflector focusing and residual moveout, but in conventional imaging workflows they are typically used only as diagnostic tools. In this work, we propose a multiscale self-attention summary network that maps high-dimensional 3D CIG volumes into compact conditioning embeddings for probabilistic subsurface velocity inversion. These learned embeddings preserve offset-dependent kinematic structure and spatial coherence while reducing variability caused by background-velocity mismatch. Conditioned on these summary embeddings, a flow-matching model learns a transport from a Gaussian source distribution to the posterior distribution of plausible velocity fields. Numerical experiments show that, compared with direct conditioning on raw CIGs, the proposed summary network improves posterior velocity inference. In particular, the multiscale attention design provides greater robustness to background-model mismatch, yielding more accurate posterior reconstructions and lower predictive uncertainty.
Sep 29, 2026

No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection

Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies span vastly different temporal scales, from sub-second point spikes to multi-hour drift patterns. However, most existing TSAD methods commit to a single temporal granularity, and multi-scale designs either analyze different scales in isolation or are constrained to a predefined coarse-to-fine hierarchy, both failing to sufficiently capture multi-scale interactions. To resolve this limitation, we propose Multi-Scale Autoencoder with Cross-Scale Attention for TSAD (MSCAD), a simple yet powerful semi-supervised TSAD framework founded on parallel autoencoder branches corresponding to different patch sizes. A stack of symmetric bidirectional cross-scale attention blocks enables every pair of scales to exchange information before reconstruction without allowing any single scale to be privileged. On the comprehensive TSB-AD benchmark (40 datasets, 530 series), MSCAD achieves large performance gains against 50 baselines across multiple metrics, with VUS-PR of 0.57(+9.6%) on the univariate split and 0.47(+9.3%) on the multivariate split compared to the state-of-the-art.
Sep 28, 2026

MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution

Gated Linear Attention (GLA) Transformers advance linear recurrent models through data-dependent gating, but face a core limitation: the fixed-capacity memory matrices across all heads operate at a single temporal resolution, where each token is processed individually, forcing them to simultaneously encode local syntactic patterns and long-range semantic structure, creating a representational bottleneck that gating alone is insufficient to resolve. We introduce Multi-Scale Gated Linear Attention (MS-GLA), which addresses this by distributing attention heads across multiple temporal resolutions. Coarser resolutions pool longer token spans naturally specializing toward long-range dependencies, while finer head groups retain sensitivity to local syntactic structure. A learnable, input-dependent fusion layer dynamically recombines head group outputs at each timestep, expanding effective memory capacity without increasing per-head state size. This multi-resolution decomposition draws on principles from Multi-Scale State-Space Models (MS-SSM), adapting them to the gated linear attention setting. We evaluate MS-GLA on language modeling, recall-intensive tasks, and long-context generalization. Across all settings, MS-GLA consistently achieves higher accuracy and lower perplexity than GLA at matched parameter counts, with up to 18.9% improvement on recall-intensive tasks and 9.5% lower average perplexity on language modeling benchmarks, validating multi-temporal resolution decomposition as a principled and effective extension of Gated Linear Attention.
Sep 25, 2026

MAGE: Towards Generalizable Multi-timescale EEG Representations

Electroencephalography (EEG) data plays an important role in understanding human brain activity, with various major applications. While current approaches, which largely build on EEG foundation models, have demonstrated strong performance across datasets and tasks, they typically rely on a fixed temporal scale. This design choice limits their ability to capture characteristics of neural dynamic behavior, often spanning across multiple timescales, which are naturally captured in EEG recordings. To address this limitation, we propose MAGE (Multi-timescale Adaptive Generalization for EEG), a foundation model that dynamically adapts to capture and integrate information across different timescales. Specifically, MAGE combines two key mechanisms: (i) a novel multi-timescale attention mechanism, capable of learning representations across multiple temporal scales and (ii) a trainable aggregation module, that dynamically identifies and adapts to the most informative timescale of the input signal. Experimental results across seven datasets demonstrate that MAGE consistently outperforms existing EEG foundation models while using substantially fewer parameters. Moreover, our results support the hypothesis that different downstream tasks benefit from distinct temporal scales.
Sep 25, 2026

Progressive Memory Transformer: Memory-Aware Attention for Time-Series

Time-series carry structure simultaneously at multiple scales (fine-grained variation, mid-range motifs, and global properties) and downstream tasks operate at correspondingly different scales. Most existing self-supervised learning approaches supervise representations globally via instance-level contrastive losses and limited temporal neighborhood supervision, but do not explicitly exploit the structural hierarchy. We propose a learning framework that explicitly enforces a structural hierarchy across three scales independently: a local objective for token alignment, a mid-range objective for window-level motifs, and a global objective for sequence-level agreement. Realizing this framework requires the backbone to expose a representation at each scale; we introduce Progressive Memory Transformer (PMT), which augments a transformer with writable, window-aligned memory that exposes the mid-range scale alongside the token and sequence-level representations conventional transformers already provide. Across eight UCR/UEA/UCI classification benchmarks, a cue-retention probe, and forecasting benchmarks, PMT learns representations that probe well at the global, mid-range, and local scales---strong low-label classification (1--5% labels), competitive forecasting performance across multiple horizons, and quantitative and qualitative evidence that memory states capture mid-range motifs.
Sep 6, 2026

MSCA-UNet: Multi-Scale Context and Attention U-Net for Image Segmentation

U-Net remains a practical baseline for image segmentation because of its simple encoder-decoder structure and skip connections. However, the bottleneck representation is still dominated by a limited set of receptive fields, while decoder features are propagated without explicitly emphasizing the most informative channels and spatial locations. This paper presents MSCA-UNet, a U-Net-based segmentation architecture that combines multi-scale contextual aggregation at the bottleneck with channel-spatial attention refinement in the decoder. The multi-scale module uses parallel atrous convolutions to capture contextual features at different receptive fields, while Convolutional Block Attention Modules (CBAMs) progressively recalibrate decoder features. Under identical experimental settings, the baseline U-Net achieves 96.9% mIoU on a held-out test set. Adding multi-scale context improves mIoU to 97.5%, while attention alone reaches 98.4%. Combining both mechanisms yields 99.1% mIoU, a 2.2 percentage-point improvement over the baseline. Parameter analysis further shows that the attention-only variant adds approximately 0.044M parameters, whereas the multi-scale module contributes most of the additional model capacity. The results support the view that multi-scale context enrichment and attention-based feature refinement provide complementary benefits within a U-Net framework.
Sep 2, 2026

EMCStereo: Attention-Enhanced Stereo Matching for Thin-Structure Depth Estimation with a Synthetic Tree-Branch Benchmark

Thin structures such as tree branches are among the hardest cases for stereo matching: a branch is only a few pixels wide, the background is cluttered, and dense ground truth for real branches is nearly impossible to label by hand. We make three contributions. First, EMCStereo integrates three lightweight attention modules into a PSMNet-style cost-volume backbone: Efficient Multi-scale Attention (EMA) on deep semantic features, a Multi-Scale Fusion block (MSFblock) learning spatial pyramid weights instead of concatenating them, and Coordinate Attention (CoordAtt) on final matching features. Because MSFblock collapses four pyramid branches into one, the modules leave the network 2.0% smaller and add only 1.7% inference time overhead. Second, VirtualTree is a synthetic stereo dataset rendered in Unreal Engine 5 with a simulated ZED Mini rig, providing 5,520 pairs with exact disparity for thin branches. Third, an eight-way ablation establishes a run-to-run noise floor of 0.009 px end-point error (EPE). EMCStereo achieves 1.31 px EPE (5.96% D1-all) on the VirtualTree test split, 1.00 px on SceneFlow, and 0.80, 0.73, 0.62, and 3.19 px on KITTI 2012, KITTI 2015, ETH3D, and Middlebury, with depth accuracy delta_1 from 92.6% to 98.7%. Evaluated against the noise floor, the attention stack is accuracy-neutral at a 100-epoch budget, while MSFblock and CoordAtt cost 0.03-0.05 px unless EMA is present.
Aug 7, 2026

HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers

Vision transformers face significant computational overheads in high-resolution dense prediction due to the quadratic complexity of self-attention. Linear attention offers efficiency but sacrifices local context modeling. We propose HSMLA (Hierarchical Softmax Multi-scale Linear Attention), which combines ReLU-based linear attention for global context, selective softmax refinement for critical local features, and multi-scale token representations via depthwise convolutions. HSMLA achieves superior accuracy-efficiency trade-offs: up to 4.2×4.2\times inference-time speedup across dense prediction tasks, 87.387.3% Dice with 3.2×3.2\times speedup on CT organ segmentation, and 94.294.2% AUC with 4.1×4.1\times speedup on pathology WSI.
Jul 27, 2026

Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform

Low-light image enhancement (LLIE) aims to improve image quality and clarity in diverse and demanding low-illumination environments. However, existing deep learning-based LLIE methods struggle to accurately capture real-world illumination and restore texture details, largely because their algorithmic strengths remain underutilized. To address these issues, we present a supervised frequency domain deep learning network for LLIE, named multi-scale attention combined with the Fourier transform (MSFT) which adopts a U-shaped, one-stage architecture that infuses guidance from low-light images into the network by channeling it through multi-scale attention. We further fuse the amplitude information from priori channels with that of the low-light image in MSFT's self-created module, and carry out multi-scale guidance along with the network. Subsequently, to better enhance the faint feature, such as fine content and textures, and to better fuse global context confidence in the decoding stage, we separately introduce a multi-shape synergistic attention and a lightweight network that effectively integrate information in high-dimensional space to embed into the superlative feature space channel containing rich texture information. Extensive experiments conducted on LOL, SID, SMID, and SDSD datasets demonstrate that MSFT significantly outperforms state-of-the-art competitors. For example, compared with Retinexformer, our method achieves a peak signal-to-noise ratio of up to 41.76 decibels on the SDSD-outdoor dataset with an increase of 11.92 decibels and a structural similarity index of 0.988 with a 13.80% improvement.
Jul 23, 2026

Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention

Streaming video diffusion models have made substantial progress toward interactive and dynamic world simulation, but the nested autoregressive and denoising loops of conventional next-frame generation hinder real-time deployment. Recent rolling-window methods pipeline denoising across multiple consecutive frames at different noise levels, improving throughput and long-horizon stability. However, they tokenize every state at the same fine spatial granularity, leaving substantial noise-dependent redundancy in the joint denoising window. We propose Ms.Forcing, an efficient streaming video generation paradigm that adapts spatial granularity to each state's noise level. Its Multi-Scale Patchification (MSP) assigns coarser patches to noisier states, reducing the active-window token count by 45%, while Multi-Scale Self-Attention (MSSA) matches the density of visible non-sink keys and values to each query scale to further reduce attention cost. Because both schedules are fixed by window position, Ms.Forcing retains a static, hardware-friendly computation graph. We further introduce Homogeneous-Noise-Level DMD (H-DMD), which assembles each fake video from clean predictions sharing the same source noise level, thereby reducing the mismatch between DMD training sequences and inference-time rollouts. The multi-scale design helps offset the additional training cost of backpropagating through overlapping windows. We include both quantitative and qualitative experiments to show that Ms.Forcing reaches 22.84 FPS on a single H200 GPU, 39.6% faster than Rolling Forcing, while significantly improving VBench scores in both short video and long video generation setting.
Jun 12, 2026

Context-Guided Semantic Alignment for Feature Fusion Networks

Feature fusion networks are fundamental components in modern object detectors, aggregating multi-scale features to detect objects of varying sizes. However, directly fusing features from different pyramid levels often introduces semantic inconsistency due to their heterogeneous representations. In this paper, we propose Feature Interaction NEtwork (FINE), a lightweight semantic alignment module that refines low-level features via high-level contextual guidance using cross-level attention prior to fusion. To bridge the structural gap and ensure computational efficiency, we introduce an Alignment-Aware Token Sampling that aligns corresponding spatial regions across scales, reducing the attention complexity by an order of magnitude. The resulting attention weights generate a spatial-channel modulation map that is upsampled and applied to the low-level features via residual element-wise modulation. This mechanism ensures that the network selectively enhances semantically relevant pixels while preserving the sub-pixel localization accuracy necessary for dense prediction tasks. FINE is generally applicable to various detectors and consistently improves detection accuracy without compromising efficiency.
Jun 4, 2026

Multiscale POD of Transformer Attention Fields: Scale-Selective Analysis via Morlet Scalogram

We introduce scale-selective Proper Orthogonal Decomposition (POD) for transformer attention fields, inspired by the use of POD for extracting energetically dominant modes from turbulent flow ensembles. The Morlet continuous wavelet transform identifies dominant temporal scales in the attention lag structure across a document ensemble; POD then extracts the energetically dominant modes at each scale from the ensemble of attention fields. The resulting modes reveal layer-dependent scale organisation, with early layers emphasising fine scales and later layers shifting toward coarser scales. We define a spectral concentration index from the POD eigenvalue decay rate and show empirically that it differentiates layers by their attention field complexity. By the classical POD optimality theorem, the extracted modes minimise the average L2 reconstruction error over the ensemble (Theorem 1), giving a data-driven effective rank for each layer. The method requires no architectural modification and no linguistic annotations: dominant attention patterns emerge from ensemble statistics alone. The turbulence analogy is structural rather than physical: we borrow ensemble covariance and modal analysis, not fluid dynamics itself.
May 15, 2026

HyperDiT: Hyper-Connected Transformers for High-Fidelity Pixel-Space Diffusion

Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental "granularity dilemma": capturing global semantics favors large patch scales, while generating high-fidelity details demands fine-grained inputs. To address this issue, we propose HyperDiT, a unified framework establishing Hyper-Connected Cross-Scale Interactions to bridge the semantic and pixel manifold. Diverging from injecting semantics by AdaLN, HyperDiT utilizes Cross-Attention mechanisms, enabling fine-grained tokens to query multi-level semantic anchors globally. To resolve the spatial mismatch during multi-scale interactions, we introduce Scale-Aware Rotary Position Embedding (SA-RoPE) to ensure precise geometric alignment among tokens of varying patch sizes. Furthermore, we incorporate Registers to learn the dense semantics from a pretrained Visual Foundation Model (VFM), effectively reducing generation hallucination and artifacts. Extensive experiments demonstrate that HyperDiT achieves state-of-the-art (SoTA) FID of 1.56\mathbf{1.56} on ImageNet 256×256256\times256 directly within the pixel space. By combining the fine-grained stream with semantic guidance, HyperDiT offers a superior paradigm for high-fidelity pixel generation.
Apr 30, 2026

An End-to-End Decision-Aware Multi-Scale Attention-Based Model for Explainable Autonomous Driving

The application of computer vision is gradually increasing across various domains. They employ deep learning models with a black-box nature. Without the ability to explain the behavior of neural networks, especially their decision-making processes, it is not possible to recognize their efficiency, predict system failures, or effectively implement them in real-world applications. Due to the inevitable use of deep learning in fully automated driving systems, many methods have been proposed to explain their behavior; however, they suffer from flawed reasoning and unreliable metrics, which have prevented a comprehensive understanding of complex models in autonomous vehicles and hindered the development of truly reliable systems. In this study, we propose a multi-scale attention-based model in which driving decisions are fed into the reasoning component to provide case-specific explanations for each decision simultaneously. For quantitative evaluation of our model's performance, we employ the F1-score metric, and also proposed a new metric called the Joint F1 score to demonstrate the accurate and reliable performance of the model in terms of Explainable Artificial Intelligence (XAI). In addition to the BDD-OIA dataset, the nu-AR dataset is utilized to further validate the generalization capability and robustness of the proposed network. The results demonstrate the superiority of our reasoning network over the classic and state-of-the-art models.
Apr 27, 2026

IMPA-Net: Meteorology-Aware Multi-Scale Attention and Dynamic Loss for Extreme Convective Radar Nowcasting

Short-range prediction of convective precipitation from weather radar observations is essential for severe weather warnings. However, deep learning models trained with pixel-wise error metrics tend to produce overly smooth forecasts that suppress intense echoes critical for hazard detection. This issue is exacerbated by insufficient multi-scale feature interaction and suboptimal fusion of heterogeneous geophysical inputs. We propose IMPA-Net (Integrated Multi-scale Predictive Attention Network), a deterministic 0-2 hour nowcasting framework that addresses these limitations through meteorologically-informed designs at the input, architecture, and loss function levels. A parameter-free Spatial Mixer reorganizes heterogeneous input channels at the mesoscale-γγ neighborhood (~2 km) via deterministic channel permutation, providing a structured cross-field prior. An integrated multi-scale predictive attention module serves as the spatiotemporal translator, capturing dynamics from mesoscale-ββ to mesoscale-γγ scales. A Meteorologically-Aware Dynamic Loss employs three-level asymmetric weighting -- adapting across training epochs, storm intensity, and forecast lead time -- to counteract regression-to-the-mean. Evaluated against seven baselines on a multi-source radar dataset over eastern China, IMPA-Net raises the Heidke Skill Score at ≥\geq45 dBZ from 0.049 (SimVP baseline) to 0.143 under matched settings. Relative to pySTEPS, it provides a better trade-off between severe-event detection and false-alarm control. Spectral analysis confirms preserved energy across mesoscale bands where competing methods show progressive smoothing. These improvements are shown within a single domain and convective regime; generalizability to other orographic and climatic regions remains to be tested.
Apr 11, 2026

Multi-modal, multi-scale representation learning for satellite imagery analysis just needs a good ALiBi

Vision foundation models have been shown to be effective at processing satellite imagery into representations fit for downstream tasks, however, creating models which operate over multiple spatial resolutions and modes is challenging. This paper presents Scale-ALiBi, a linear bias transformer attention mechanism with a spatial encoding bias to relationships between image patches at different ground sample distance scales. We provide an implementation of Scale-ALiBi over a dataset of aligned high- and low-resolution optical and low-resolution SAR satellite imagery data using a triple-contrastive and reconstructive architecture, show an improvement on the GEO-Bench benchmark, and release the newly curated dataset publicly.
Apr 11, 2026

A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction

Learning multi-scale representations is the common strategy to tackle object scale variation in dense prediction tasks. Although existing feature pyramid networks have greatly advanced visual recognition, inherent design defects inhibit them from capturing discriminative features and recognizing small objects. In this work, we propose Asymptotic Content-Aware Pyramid Attention Network (A3-FPN), to augment multi-scale feature representation via the asymptotically disentangled framework and content-aware attention modules. Specifically, A3-FPN employs a horizontally-spread column network that enables asymptotically global feature interaction and disentangles each level from all hierarchical representations. In feature fusion, it collects supplementary content from the adjacent level to generate position-wise offsets and weights for context-aware resampling, and learns deep context reweights to improve intra-category similarity. In feature reassembly, it further strengthens intra-scale discriminative feature learning and reassembles redundant features based on information content and spatial variation of feature maps. Extensive experiments on MS COCO, VisDrone2019-DET and Cityscapes demonstrate that A3-FPN can be easily integrated into state-of-the-art CNN and Transformer-based architectures, yielding remarkable performance gains. Notably, when paired with OneFormer and Swin-L backbone, A3-FPN achieves 49.6 mask AP on MS COCO and 85.6 mIoU on Cityscapes. Codes are available at https://github.com/mason-ching/A3-FPN.
Apr 10, 2026

Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS)

Glioma is a harmful brain tumor that requires early detection to ensure better health results. Early detection of this tumor is key for effective treatment and requires an automated segmentation process. However, it is a challenging task to find tumors due to tumor characteristics like location and size. A reliable method to accurately separate tumor zones from healthy tissues is deep learning models, which have shown promising results over the last few years. In this research, an Adaptive Dual Residual U-Net with Attention Gate and Multiscale Spatial Attention Mechanisms (ADRUwAMS) is introduced. This model is an innovative combination of adaptive dual residual networks, attention mechanisms, and multiscale spatial attention. The dual adaptive residual network architecture captures high-level semantic and intricate low-level details from brain images, ensuring precise segmentation of different tumor parts, types, and hard regions. The attention gates use gating and input signals to compute attention coefficients for the input features, and multiscale spatial attention generates scaled attention maps and combines these features to hold the most significant information about the brain tumor. We trained the model for 200 epochs using the ReLU activation function on BraTS 2020 and BraTS 2019 datasets. These improvements resulted in high accuracy for tumor detection and segmentation on BraTS 2020, achieving dice scores of 0.9229 for the whole tumor, 0.8432 for the tumor core, and 0.8004 for the enhancing tumor.
Apr 10, 2026

Hierarchical Kernel Transformer: Multi-Scale Attention with an Information-Theoretic Approximation Analysis

The Hierarchical Kernel Transformer (HKT) is a multi-scale attention mechanism that processes sequences at L resolution levels via trainable causal downsampling, combining level-specific score matrices through learned convex weights. The total computational cost is bounded by 4/3 times that of standard attention, reaching 1.3125x for L = 3. Four theoretical results are established. (i) The hierarchical score matrix defines a positive semidefinite kernel under a sufficient condition on the symmetrised bilinear form (Proposition 3.1). (ii) The asymmetric score matrix decomposes uniquely into a symmetric part controlling reciprocal attention and an antisymmetric part controlling directional attention; HKT provides L independent such pairs across scales, one per resolution level (Propositions 3.5-3.6). (iii) The approximation error decomposes into three interpretable components with an explicit non-Gaussian correction and a geometric decay bound in L (Theorem 4.3, Proposition 4.4). (iv) HKT strictly subsumes single-head standard attention and causal convolution (Proposition 3.4). Experiments over 3 random seeds show consistent gains over retrained standard attention baselines: +4.77pp on synthetic ListOps (55.10+-0.29% vs 50.33+-0.12%, T = 512), +1.44pp on sequential CIFAR-10 (35.45+-0.09% vs 34.01+-0.19%, T = 1,024), and +7.47pp on IMDB character-level sentiment (70.19+-0.57% vs 62.72+-0.40%, T = 1,024), all at 1.31x overhead.
Apr 9, 2026

Generative 3D Gaussian Splatting for Arbitrary-ResolutionAtmospheric Downscaling and Forecasting

While AI-based numerical weather prediction (NWP) enables rapid forecasting, generating high-resolution outputs remains computationally demanding due to limited multi-scale adaptability and inefficient data representations. We propose the 3D Gaussian splatting-based scale-aware vision transformer (GSSA-ViT), a novel framework for arbitrary-resolution forecasting and flexible downscaling of high-dimensional atmospheric fields. Specifically, latitude-longitude grid points are treated as centers of 3D Gaussians. A generative 3D Gaussian prediction scheme is introduced to estimate key parameters, including covariance, attributes, and opacity, for unseen samples, improving generalization and mitigating overfitting. In addition, a scale-aware attention module is designed to capture cross-scale dependencies, enabling the model to effectively integrate information across varying downscaling ratios and support continuous resolution adaptation. To our knowledge, this is the first NWP approach that combines generative 3D Gaussian modeling with scale-aware attention for unified multi-scale prediction. Experiments on ERA5 show that the proposed method accurately forecasts 87 atmospheric variables at arbitrary resolutions, while evaluations on ERA5 and CMIP6 demonstrate its superior performance in downscaling tasks. The proposed framework provides an efficient and scalable solution for high-resolution, multi-scale atmospheric prediction and downscaling. Code is available at: https://github.com/binbin2xs/weather-GS.
Apr 8, 2026

MSGL-Transformer: A Multi-Scale Global-Local Transformer for Rodent Social Behavior Recognition

Recognition of rodent behavior is important for understanding neural and behavioral mechanisms. Traditional manual scoring is time-consuming and prone to human error. We propose MSGL-Transformer, a Multi-Scale Global-Local Transformer for recognizing rodent social behaviors from pose-based temporal sequences. The model employs a lightweight transformer encoder with multi-scale attention to capture motion dynamics across different temporal scales. The architecture integrates parallel short-range, medium-range, and global attention branches to explicitly capture behavior dynamics at multiple temporal scales. We also introduce a Behavior-Aware Modulation (BAM) block, inspired by SE-Networks, which modulates temporal embeddings to emphasize behavior-relevant features prior to attention. We evaluate on two datasets: RatSI (5 behavior classes, 12D pose inputs) and CalMS21 (4 behavior classes, 28D pose inputs). On RatSI, MSGL-Transformer achieves 75.4% mean accuracy and F1-score of 0.745 across nine cross-validation splits, outperforming TCN, LSTM, and Bi-LSTM. On CalMS21, it achieves 87.1% accuracy and F1-score of 0.8745, a +10.7% improvement over HSTWFormer, and outperforms ST-GCN, MS-G3D, CTR-GCN, and STGAT. The same architecture generalizes across both datasets with only input dimensionality and number of classes adjusted.
Apr 7, 2026

Cross-Stage Attention Propagation for Efficient Semantic Segmentation

Recent lightweight semantic segmentation methods have made significant progress by combining compact backbones with efficient decoder heads. However, most multi-scale decoders compute attention independently at each feature scale, introducing substantial redundancy since the resulting attention distributions across scales are strongly correlated. We propose Cross-Stage Attention Propagation (CSAP), a decoder framework that computes attention at the deepest feature scale and propagates the resulting attention maps to shallower stages, bypassing query-key computation at those stages entirely. This design preserves multi-scale contextual reasoning while substantially reducing the decoder's computational cost. CSAP-Tiny achieves 42.9% mIoU on ADE20K with only 5.5 GFLOPs, 80.5% on Cityscapes with 21.5 GFLOPs, and 40.9% on COCO-Stuff 164K with 5.5 GFLOPs, surpassing SegNeXt-Tiny by +1.8% on ADE20K while requiring 16.8% fewer floating-point operations.
Mar 30, 2026

Skillful Kilometer-Scale Regional Weather Forecasting via Global and Regional Coupling

Data-driven weather models have advanced global medium-range forecasting, yet high-resolution regional prediction remains challenging due to unresolved multiscale interactions between large-scale dynamics and small-scale processes such as terrain-induced circulations and coastal effects. This paper presents a global-regional coupling framework for kilometer-scale regional weather forecasting that synergistically couples a pretrained Transformer-based global model with a high-resolution regional network via a novel bidirectional coupling module, ScaleMixer. ScaleMixer dynamically identifies meteorologically critical regions through adaptive key-position sampling and enables cross-scale feature interaction through dedicated attention mechanisms. The framework produces forecasts at 0.05∘0.05^\circ (∼5km\sim 5 \mathrm{km} ) and 1-hour resolution over China, significantly outperforming operational NWP and AI baselines on both gridded reanalysis data and real-time weather station observations. It exhibits exceptional skill in capturing fine-grained phenomena such as orographic wind patterns and Foehn warming, demonstrating effective global-scale coherence with high-resolution fidelity. The code is available at https://anonymous.4open.science/r/ScaleMixer-6B66.