Aug 2026· IEEE Transactions on Neural Networks and Learning Systems· Vol PP, pp. 1-11· 0 citations
Medicine
TL;DR
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 during inference with zero additional computational overhead.
Abstract
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.
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.
Xiaojie Chen, Yi-Fei Zhou, Yi-Ming Zhou et al.· International Conference on...· 0 citations
LCA-Net is presented, a computationally efficient framework for small object detection that balances accuracy with model complexity that demonstrates a favorable accuracy–efficiency trade-off for real-time traffic perception.
Shan Lin, Ben-Sheng Yun, Zhenyu Lin et al.· Information· 0 citations
The proposed framework features a redesigned cross-scale feature fusion module, CCFM-S2, which utilizes the SPD-Conv operator for information preserving downsampling and explicitly integrates high-resolution shallow features (S2 layer), thereby infusing indispensable spatial details into the feature hierarchy for small targets.
Remote sensing object detection is a fundamental task in ground scene observation and analysis. Despite the currently discrete-frame detectors achieves remarkable performance, they still suffer from three critical limitations: 1) mainstream architectures regress spatial locations independently, making it difficult to exploit cross-frame temporal cues for disambiguating occlusions and motion blur; 2) the high-frequency details are prone to degradation during long-term temporal modeling in the complex remote sensing backgrounds where the foreground and background are highly similar, leading to memory disturbance; and 3) traditional feature pyramid networks (FPNs) merely adopt simple concatenation to fuse multiscale feature maps, neglecting the synergy between shallow details and deep semantics. To address these issues, we propose the Frequency-enhanced spatiotemporal model (FSM). Specifically, we utilize a streaming inference pipeline to continuously process image sequences and build upon the state space model (SSM) to develop the spatiotemporal Mamba module (SMM) that dynamically memorizes and updates target location states across consecutive frames. Moreover, we construct a frequency enhancement module (FEM) to counteract feature degradation in long temporal sequences under challenging remote sensing backgrounds, generating more discriminative temporal representations for the SSM. In addition, we design an adaptive bidirectional FPN (ABiFPN) to selectively fuse shallow and deep features through a learnable scalar mechanism, restoring the small target information forgotten in deep layers and achieving fine-grained feature synergy. Experimental results demonstrate that the proposed FSM achieves 76.6% and 38.7% mAP@0.5:0.95 on the EMRS-Frame and SAT-MTB datasets, outperforming all current state-of-the-art detection methods.
Shi-Long Jing, Heng-Yi Lv, Yu-Chen Zhao et al.· IEEE Geoscience and Remote S...· 0 citations
For object detection in remote sensing images, foggy conditions tend to degrade image quality by scattering light and obscuring critical details, thereby compromising the performance of the involved detection models. To address this challenge, we first analyze the feature response of the Laplacian operation based on the atmospheric scattering model (ASM) and design two complementary Laplacian templates for bidirectional edge extraction and fuse them into a customized convolution kernel to enhance fog-degraded features. A rotated object detection method based on masked clean feature distillation is proposed, which leverages clean image features to facilitate the learning of fog-degraded image features. A dual-stream feature attention fusion module is then adopted to integrate the original yet blurred predistillation features with the clear but potentially noisy postdistillation features generated by the feature adjustment module, thus rendering the features for more effective object detection. Finally, a bidirectional attention-based feature pyramid network (BI-AFPN) is employed to enhance multilevel feature fusion. Extensive experiments on the dataset for object detection In optical remote-sensing images (DIOR)-Foggy, dataset for object detection in aerial images (DOTA)-Foggy, and real-world RDDTS fog datasets demonstrate that the proposed model outperforms other state-of-the-art methods.
Wei-Zhi Yang, Jiangqun Ni, Yi Xie· IEEE Transactions on Geoscie...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
