Jul 2026· International Conference on Multimedia and Image Processing· Vol 14298, pp. 1429804 - 1429804-12· 0 citations· 26 references
Engineering
TL;DR
GPE-YOLO is proposed, a robust detection framework built upon the YOLOv11 architecture that explicitly integrates multiscale edge priors to enhance feature resilience and validate the potential of GPE-YOLO for reliable deployment in real-world adverse weather scenarios.
Abstract
Although deep learning-based object detectors have achieved remarkable performance on standard benchmarks, their reliability deteriorates significantly under adverse weather conditions (e.g., rain, snow, and fog) due to severe image degradation and the loss of critical structural information. To address this challenge, this paper proposes GPE-YOLO, a robust detection framework built upon the YOLOv11 architecture that explicitly integrates multiscale edge priors to enhance feature resilience. Specifically, we introduce three novel components: 1) Dual-Stream Gradient-Pooling Stem (DSGPS) serves as an efficient preprocessing unit, utilizing parallel 3D Sobel and spatial convolutions to capture comprehensive low-level features and mitigate noise propagation at the input stage. 2) The Pyramidal Edge Prior Generation Module (PEPGM) extracts multi-scale edge maps from shallow layers and injects them into the backbone network via max pooling, effectively suppressing background interference while preserving structural details. 3) The Dynamic Edge-Aware Feature Pyramid (DE-AFP) incorporates DySample and CSPStage to optimize feature upsampling and downsampling processes, thereby ensuring efficient semantic information transmission and robust multi-scale fusion across the network. Extensive experiments on the VOC2012-CWC dataset demonstrate the superiority of our method. GPE-YOLO achieves an mAP@0.5 of 32.84% and mAP@0.5:0.95 of 24.59%, outperforming the baseline YOLOv11 by substantial margins of 4.85% and 3.86%, respectively. These results validate the potential of GPE-YOLO for reliable deployment in real-world adverse weather scenarios.
In unconstrained environments such as aerial and surveillance imagery, achieving precise detection of small objects continues to pose significant challenges in computer vision because of constrained pixel data and cluttered backgrounds, and high sensitivity to bounding box localization errors. Although existing detectors have made progress, they often suffer from the gradual loss of fine-grained features in deep networks and inefficient multiscale feature fusion. Motivated by these challenges, this study designs the HASO-DETR small object detection algorithm.The proposed framework features three key contributions: 1 The Hybrid Dilated Residual Attention Block (HDRAB) embedded in the backbone network, which employs multi-scale dilated convolutions and channel attention mechanisms to enhance and preserve critical features of small objects during downsampling stages; 2 A redesigned cross-scale feature fusion module, CCFM-S2, which utilizes the SPD-Conv operator for informationpreserving downsampling and explicitly integrates high-resolution shallow features (S2 layer), thereby infusing indispensable spatial details into the feature hierarchy for small targets; 3 The adoption of Employing the NormalizedWasserstein Distance (NWD) as a regression loss, we model bounding boxes as Gaussian distributions to effectively reduce sensitivity to minor deviations in bounding box coordinates. Extensive experiments on challenging benchmark datasets VisDrone2019 , demonstrate that HASO-DETR sets a new state-of-the-art performance, outperforming numerous mainstream detectors.
Visual degradation caused by adverse meteorological conditions, such as low light and rain, significantly hinders the deployment of salient object detection (SOD) on edge devices. Existing methods often rely on computationally expensive restoration preprocessing or complex feature stacking, making real-time inference difficult. To address these challenges, this article proposes a novel lightweight model, termed the robust elastic adaptive difference network (READNet). The core innovation lies in a novel elastic pixel differential convolution operator, which flexibly captures microscopic gradient cues to effectively coordinate high-level semantics with low-level details. This operator is further embedded into an inverted residual block through a multibranch structural reparameterization, enabling structure-aware feature enhancement during inference with zero additional computational overhead. Furthermore, to mitigate nonuniformly distributed environmental noise, a condition-adaptive dual gate is introduced. The module innovatively integrates second-order variance statistics and contextual difference mechanisms to adaptively recalibrate features across both channel and spatial dimensions. Experimental results demonstrate that READNet achieves state-of-the-art performance on challenging benchmarks, validating its superior parameter efficiency and suitability for real-time applications. The source code is publicly available at https://github.com/TurnHug/READNet.git.
Weiyi Wei, Yongxin Shi, Shengxia Gao et al.· IEEE Transactions on Neural...· 0 citations
Object detection in optical remote sensing imagery is severely affected by adverse weather conditions, such as fog and haze, which degrade image quality and obscure structural details. Although recent Transformer-based detectors have achieved promising performance, they suffer from quadratic computational complexity for high-resolution inputs and tend to produce imprecise object boundaries in degraded scenes. To address these issues, we propose an Edge-Guided State-Space DETR (ES-DETR), an end-to-end detection framework that integrates linear-complexity state-space modeling with structural priors. Specifically, a Laplacian Edge-Aware Module (LEM) is designed to extract high-frequency boundary information from foggy images. Moreover, a Structural-Prior-Driven Mamba Fusion Module (SMF) is introduced to incorporate edge-derived structural priors into the Mamba architecture for long-range dependency modeling and feature fusion. This design effectively restores degraded semantic representations. Extensive experiments on foggy remote sensing benchmarks demonstrate that the proposed ES-DETR outperforms state-of-the-art detectors while maintaining a favorable accuracy–efficiency trade-off.
Xiaopeng Yang, Qiang Zhang, Zheng Liang et al.· IEEE Signal Processing Lette...· 0 citations
Remote sensing ship detection plays a pivotal role in maritime surveillance, safety assurance, and traffic management. However, current detection methods often face significant challenges due to complex sea-surface background noise, large target-scale variations, and edge-hardware limitations. In this paper, we propose RepLite-YOLO, a lightweight detection framework based on YOLOv11n. Specifically, to alleviate irreversible spatial information loss during downsampling, we adopt the ADown module, originally introduced in YOLOv9, to generate spatially complementary features through its two-branch downsampling mechanism. This design helps preserve salient hull-edge responses while suppressing part of the random sea-surface interference, thereby improving feature robustness for small ship targets. To achieve substantial structural streamlining while maintaining competitive representational capacity under strict hardware constraints, we design the C3k2_OREPA_RS module, utilizing online re-parameterization (OREPA) to efficiently reconstruct deep layers without additional re-parameterization-induced inference operations. Furthermore, we construct the ELANFusion_Block by integrating Depthwise Separable Convolutions (DSC) into the ELAN paradigm to alleviate the multi-scale aggregation bottleneck, and tailor the Detect_DWLite head for highly compressed decoupled prediction. Experimental results show that RepLite-YOLO achieves a favorable balance between detection accuracy and computational efficiency. Compared with YOLOv11n, it reduces the number of parameters by 57.4% and GFLOPs by 49.2%, while maintaining competitive detection accuracy with slight mAP@50 improvements of 1.2 and 1.3 percentage points on the Vessel dataset and Ship Detection dataset, respectively.
Ruijia Fu, Zuomin Wang, Zijun Lin et al.· Remote Sensing· 0 citations
In recent years, object detection methods for adverse weather conditions have developed rapidly, alleviating to some extent the significant performance degradation of conventional object detection methods caused by image degradation. However, existing object detection methods still struggle to effectively represent weak target cues, such as edges, textures, and local structural information. These fragile features are further lost during downsampling, thereby limiting detection performance. To address this issue, we propose DFE-RFC, which enhances feature representation and information preservation under complex degradations through the joint introduction of degradation feature enhancement and robust feature compression. Specifically, we design a Degradation Feature Enhancement (DFE) module, which incorporates a degradation response map and a residual modulation mechanism into a channel and spatial attention framework, thereby enhancing the network’s ability to represent target edges, textures, and local structures in degraded scenes. In addition, we propose a Robust Feature Compression (RFC) method, which introduces an auxiliary pooling branch during downsampling to compensate the compressed output of the main branch with structural information, thereby preserving key discriminative information and reducing the loss of fine details caused by spatial compression. Experimental results on the DAWN adverse weather dataset demonstrate that the proposed DFE-RFC method achieves promising detection performance and verify the effectiveness of the proposed method.
Hao Sun, Jingyu Li, Yilei Huang et al.· 2026 IEEE International Conf...· 0 citations
Infrared (IR) video target detection is important for long-range target perception in anti-UAV systems under complex lighting and background conditions. However, long-range tiny unmanned aerial vehicles (UAVs) usually occupy only a few pixels, exhibit weak thermal contrast, and are easily disturbed by cluttered backgrounds such as clouds, buildings, vegetation, feature edges, and thermal noise. Although YOLO-style detectors provide high real-time performance, their feature flow is prone to weak target response attenuation during downsampling, contextual ambiguity in deep feature representation, and background clutter propagation during cross-scale fusion. To address these degradation problems, this paper proposes FDR-YOLO, a feature-degradation-aware feature-flow reconstruction network based on YOLOv26. Specifically, LAE-based response-preserving downsampling (LAE-RPD) preserves weak but discriminative target responses during spatial compression; lightweight U-shaped dilated context aggregation (UCDC-Lite) enhances deep contextual discrimination between tiny UAV targets and cluttered backgrounds; and high-frequency prior-guided semantic injection fusion (HPG-SIF) uses shallow high-frequency priors to constrain the injection of deep semantic features. Experiments on multiple datasets show that FDR-YOLO improves detection accuracy while retaining lightweight and low-latency characteristics. On the Anti-UAV dataset, FDR-YOLO improves mAP50 and mAP50–95 by 3.0 and 3.3 percentage points, respectively, over YOLOv26s. Additional experiments on InfraredUAV and the RGB-based UAVSwarm dataset demonstrate the applicability of the proposed design to another infrared benchmark and to visible-light UAV detection under dataset-specific training.