Aug 2026· Signal, Image and Video Processing· Vol 20· 0 citations· 36 references
Computer Science
TL;DR
The Local Dilated Convolution module and its lightweight variant, Ghost-LDC are introduced and it is shown that LDC-based modules can improve performance in some tested dense prediction settings, while the semantic segmentation results are more configuration-sensitive.
A global-local fusion segmentation model named global-local bubble network is designed, which uses the visual state space encoder as the backbone for feature extraction and establishes long-range pixel dependencies, significantly enhancing context inference capabilities under dense occlusion.
Mi Wang, Kai-Jie Tong, Xin-Xin Li et al.· The Physics of Fluids· 0 citations
Experiments show that EDC outperforms state-of-the-art deformable convolution variants, including Deformable ConvNets V1-V4 and Entire Deformable ConvNets, across mainstream segmentation datasets with various decoder settings, and ablation studies confirm the effectiveness of each component.
Yi-Xiao Li, Xiao-Yuan Yang, Jin Jiang et al.· 0 citations
The proposed WMW-SAM, a Weighted Multi-Scale and Wavelet-Enhanced SAM, is designed to handle limitations of existing adaptation strategies for SOD, and develops the Weighted Multi-Scale Adapter (WMSA), which utilizes learnable weighting across multiple receptive fields to calibrate features of different scales.
Accurate retinal vessel segmentation is an important foundation for assisted screening and quantitative analysis of ophthalmic diseases and systemic diseases. However, the edge and high-frequency responses of thin, low-contrast vessels are easily attenuated during successive convolution operations and multilevel downsa...
Lu Cao, Jia-Ming He, Yan-Hua Liang et al.· 2026 2nd International Confe...· 0 citations
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.
Wei-Yi Wei, Yongxin Shi, Shengxia Gao et al.· IEEE Transactions on Neural...· 0 citations
The Regional Self-Attention Mechanism is proposed, which strictly confines the self-attention operation to the independent regions defined by the target bounding boxes, enabling the model to generate specific-category targets in a targeted manner during the denoising process.
Haoshu Zhao, Xi Zhang· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.