3 papers
cs.CV2025
WaveSeg: Enhancing Segmentation Precision via High-Frequency Prior and Mamba-Driven Spectrum Decomposition
Guoan Xu, Yang Xiao, Wenjing Jia +3
While recent semantic segmentation networks heavily rely on powerful pretrained encoders, most employ simplistic decoders, leading to suboptimal trade-offs between semantic context…
cs.CV2025
S2AFormer: Strip Self-Attention for Efficient Vision Transformer
Guoan Xu, Wenfeng Huang, Wenjing Jia +3
Vision Transformer (ViT) has made significant advancements in computer vision, thanks to its token mixer's sophisticated ability to capture global dependencies between all tokens.…
cs.CV2025
Learning Dual-Domain Multi-Scale Representations for Single Image Deraining
Shun Zou, Yi Zou, Mingya Zhang +3
Existing image deraining methods typically rely on single-input, single-output, and single-scale architectures, which overlook the joint multi-scale information between external an…