6 papers
Lean Learning Beyond Clouds: Efficient Discrepancy-Conditioned Optical-SAR Fusion for Semantic Segmentation
Chenxing Meng, Wuzhou Quan, Yingjie Cai +3
Cloud occlusion severely degrades the semantic integrity of optical remote sensing imagery. While incorporating Synthetic Aperture Radar (SAR) provides complementary observations,…
Attention Residuals
Kimi Team, Guangyu Chen, Yu Zhang +34
Residual connections with PreNorm are standard in modern LLMs, yet they accumulate all layer outputs with fixed unit weights. This uniform aggregation causes uncontrolled hidden-st…
M2IR: Proactive All-in-One Image Restoration via Mamba-style Modulation and Mixture-of-Experts
Shiwei Wang, Yongzhen Wang, Bingwen Hu +3
While Transformer-based architectures have dominated recent advances in all-in-one image restoration, they remain fundamentally reactive: propagating degradations rather than proac…
AlignFreeNet: Is Cross-Modal Pre-Alignment Necessary? An End-to-End Alignment-Free Lightweight Network for Visible-Infrared Object Detection
Dingkun Zhu, Haote Zhang, Lipeng Gu +7
Cross-modal misalignments, such as spatial offsets, resolution discrepancies, and semantic deficiencies, frequently occur in visible-infrared object detection (VI-OD). To mitigate…
Perceive, Act and Correct: Confidence Is Not Enough for Hyperspectral Classification
Muzhou Yang, Wuzhou Quan, Mingqiang Wei
Confidence alone is often misleading in hyperspectral image classification, as models tend to mistake high predictive scores for correctness while lacking awareness of uncertainty.…
Equal is Not Always Fair: A New Perspective on Hyperspectral Representation Non-Uniformity
Wuzhou Quan, Mingqiang Wei, Jinhui Tang
Hyperspectral image (HSI) representation is fundamentally challenged by pervasive non-uniformity, where spectral dependencies, spatial continuity, and feature efficiency exhibit co…