cs.CVSep 19, 2026

HDMamba-YOLO: Efficient State-Space Perception and Local Spatial Reconstruction for UAV Small Object

Authors: Linduo Wei, Junjie Fan, Yijun Mai, Yong Qi

Organizations: School of Economics and Management, Nanjing University of Science and Technology, Nanjing, 210094, China · School of Intellectual Property, Nanjing University of Science and Technology, Nanjing, 210094, China · School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Small-object detection in UAV imagery is challenged by weak visual evidence, ambiguous boundaries, dense object distributions, and complex backgrounds. Effective detection therefore requires long-range contextual information for target-background discrimination while preserving explicit local two-dimensional structures for accurate localization. These requirements arise at different stages of the detection pipeline and are not naturally addressed by a uniform feature-processing strategy. We propose Hybrid Dual-domain Mamba-YOLO (HDMamba-YOLO), a stage-wise heterogeneous SSM-CNN detector organized according to a perception-reconstruction-alignment-interaction rationale. EfficientVMamba-based EVSS establishes long-range contextual perception in the backbone, while PhasePatchMerging2D provides phase-aware hierarchical transitions. DST-Wrapper and Native C3k2-ASSAF then perform perception-to-reconstruction transition and repeated local two-dimensional reconstruction during FPN/PAN aggregation. DySample provides content-adaptive cross-scale resampling, while OS-CVTIA introduces macro-micro interaction and task-specific modulation for localization and classification. On VisDrone2019, HDMamba-YOLO-B achieves 42.737% mAP50 and 25.713% mAP50:95 with 10.042M parameters and 29.879 corrected GFLOPs. HDMamba-YOLO-Lite achieves 41.140% mAP50 and 24.741% mAP50:95 with 5.344M parameters. Under the unified AI-TOD evaluation protocol, HDMamba-YOLO-B obtains 21.621% AP and 47.881% AP50. Controlled ablations further support the stage-wise allocation of state-space perception, convolutional reconstruction, dynamic alignment, and task interaction for UAV small-object detection.

Figures & tables

Figure 1: Overall architecture and functional pipeline of HDMamba-YOLO-B. The detector follows a perception–reconstruction–alignment–interaction design: EVSS performs efficient contextual perception and PhasePatchMerging2D constructs phase-aware hierarchical transitions; DST-Wrapper and Native C3k2-ASSAF form an ASSAF-centered local reconstruction pathway; DySample provides content-adaptive cross-scale alignment; and OS-CVTIA performs classification–localization interaction before the native YOLO prediction branches.
Figure 2: P–R–A–I functional rationale and stage-wise operator allocation in HDMamba-YOLO-B. State-space modeling is assigned primarily to long-range contextual perception, CNN-style processing is retained for local two-dimensional reconstruction, DySample provides content-adaptive cross-scale resampling, and OS-CVTIA performs macro–micro interaction for localization and classification. DST-Wrapper acts as the transition between perception and reconstruction. The reconstructed and aligned multi-scale features are P3P3 ( 80×80×6480\times 80\times 64 ), P4P4 ( 40×40×12840\times 40\times 128 ), and P5P5 ( 20×20×19220\times 20\times 192 ). This figure is a functional abstraction rather than a complete layer-wise topology.
Figure 3: Detection-adapted EVSS block used in the contextual perception stage. The block combines ES2D-based selective state-space propagation with a lightweight local path composed of depthwise convolution, Batch Normalization, GELU, and pointwise projection, followed by shared BiAttn calibration, residual updating, and an MLP transformation.
Figure 4: Mechanism of PhasePatchMerging2D. The input feature is decomposed into four parity-defined spatial phases, concatenated in the implementation order [X00,X10,X01,X11][X_{00},X_{10},X_{01},X_{11}] , converted to channel-last layout for LayerNorm and bias-free linear projection, and then returned to channel-first layout. Optional zero padding is applied only to the bottom and/or right boundary when an input dimension is odd.
Figure 5: ASSAF-centered local spatial reconstruction pathway. (a) ASSAF combines directionally factorized local-detail modeling and fixed-grid large-kernel contextual modeling with independent dual-sigmoid calibration and gated additive reconstruction. (b) DST-Wrapper reuses the ASSAF mechanism to re-encode the deepest backbone feature at the perception–reconstruction interface. (c) Native C3k2-ASSAF embeds ASSAF into the native C2f/C3k2 split–iterate–concatenate topology and retains the initial partitions and intermediate ASSAF responses for progressive feature reuse; the canonical HDMamba-YOLO-B configuration uses N=1N=1 .
Figure 6: Mechanism of DySample-based dynamic spatial alignment. A 1×11\times 1 offset predictor generates content-dependent residual offsets, which are combined with fixed sub-pixel initialization and the pixel-center base grid. After coordinate normalization and rearrangement, the resulting dynamic grid resamples grouped feature values using bilinear grid_sample . In HDMamba-YOLO-B, g=4g=4 and s=2s=2 ; padding_mode=border and align_corners=False are used.
Figure 7: Structure of OS-CVTIA and its native YOLO prediction interface. Four macro/micro boundary–context responses are blended using α\alpha and converted into asymmetric localization and classification masks. The masks modulate the shared feature through learnable residual amplitudes before the native regression ( cv2 +DFL) and classification ( cv3 ) branches. In the final configuration, α=0.5\alpha=0.5 , λ=0.1\lambda=0.1 , λα=0.05\lambda\alpha=0.05 , and γbox=γcls=0.01\gamma_{box}=\gamma_{cls}=0.01 at initialization.
DatasetCategoriesTraining imagesValidation images
VisDrone2019106,471548
AI-TOD811,2142,804
Table 1: Dataset splits used in the experiments.
Figure 8: Accuracy–complexity comparison on the VisDrone2019 validation set. The horizontal axis denotes reported or corrected GFLOPs, the vertical axis denotes mAP 50:95 , and marker area is proportional to the number of parameters. Marker shapes distinguish detector families, while the connected diamond markers indicate the Tiny, Lite, and Base configurations of HDMamba-YOLO.
Figure 9: Feature-response comparison on representative VisDrone2019 validation scenes. Rows (a)–(c) represent dense mixed traffic and pedestrian clusters, low-contrast vehicles against cluttered road backgrounds, and densely packed distant targets with partial occlusion, respectively. Columns show the input image, YOLO11s response, and HDMamba-YOLO-B response, respectively. Responses are extracted from the P3 pre-detection feature (stride 8) and summarized by channel-wise root-mean-square activation. Within each row, the two models use the same normalization scale; warmer colors indicate larger normalized responses.
Figure 10: Qualitative detection comparison on representative VisDrone2019 validation scenes. The three rows follow the same scene order and challenge categories as Fig. 9 , enabling a direct comparison between feature-response patterns and the corresponding detection outcomes. Columns show the ground-truth annotations, YOLO11s predictions, and HDMamba-YOLO-B predictions, respectively. Orange boxes indicate ground-truth instances. In the prediction panels, green and blue solid boxes denote true-positive (TP) and false-positive (FP) detections, respectively, while red dashed boxes indicate unmatched ground-truth objects (FN). Visual matching uses class-consistent one-to-one assignment at an IoU threshold of 0.5; detections are shown at a confidence threshold of 0.25 with an NMS IoU threshold of 0.7.
Figure 11: Scale-aware qualitative detection comparison on the official AI-TOD validation set. Rows (a)–(c) correspond to a very-tiny-dominated scene (image 1697), a tiny-object scene (image 1043), and a mixed tiny/small scene (image 1845), respectively. Columns show Ground Truth, YOLO11s, and HDMamba-YOLO-B. Orange boxes denote ground-truth instances; green and blue solid boxes in prediction panels denote TP and FP detections, while red dashed boxes denote unmatched ground-truth objects (FN). Purple rectangles indicate the ground-truth-driven regions shown in the enlarged views, and the same region is used across the three columns of each row.
Figure 12: Internal response patterns of the full ASSAF block on two representative VisDrone regions. Columns show the input region, Local-detail response, Context response, and fused ASSAF response. The three response maps are extracted from the same forward pass. For visualization, each response is independently normalized using its 1st–99th percentile range; therefore, color intensity reflects the within-branch spatial distribution rather than absolute activation magnitude across branches.
Detection headInteraction designP (%)R (%)mAP 50 (%)mAP 50:95 (%)
Native Detect–53.74740.52542.38825.569
OS-CVTIA-H2Weakened micro interaction52.03241.70642.60325.533
OS-CVTIA-H1Full interaction + relaxation53.36741.57242.73725.713
Table 9: Ablation of OS-CVTIA interaction designs on VisDrone2019.
Figure 13: Training convergence on VisDrone2019 for YOLO11s and HDMamba-YOLO-B. The two panels report validation mAP 50:95 and validation box loss, respectively. Both models exhibit stable optimization, while HDMamba-YOLO-B converges to a higher validation accuracy and a lower box-loss level. The figure is intended to compare final optimization behavior rather than convergence speed.

Explore similar work

CardsList

  1. YOLO12-MambaScan: An Efficient Object Detector with High-Frequency Enhancement and State-Space Modeling

    Sep 12, 2026Hao WangAerial Object DetectionRemote Sensing Small Object Detection

    BDNRC

  2. CollabOD: Collaborative Multi-Backbone with Cross-scale Vision for UAV Small Object Detection

    Mar 6, 2026Xuecheng Bai, Yuxiang Wang, Chuanzhi Xu +3Remote Sensing Small Object DetectionSmall Object Detection

    Aviation Traffic Control Technology (SHENZHEN) Co., Ltd., Shenzhen, China · The University of Sydney, NSW, Australia · Research Institute of Traffic Control Technology Co., Ltd., Beijing, China +1

  3. ScopeMamba-YOLO: Widening the Perceptual Scope Inward and Outward for Small Object Detection in Remote Sensing Imagery

    Sep 9, 2026Junjie Fan, Yijun Mai, Linduo Wei +5Remote Sensing Image UnderstandingRemote Sensing Small Object Detection

    School of Intellectual Property, Nanjing University of Science and Technology, Nanjing 210094, China · School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · School of Economics and Management, Nanjing University of Science and Technology, Nanjing 210094, China