5 papers
SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention
Ruibang Li, Guan Luo, Yiwei Zhang +3
Standard softmax self-attention excels in vision tasks but incurs quadratic complexity O(N^2), limiting high-resolution deployment. Linear attention reduces the cost to O(N), yet i…
Integrating Diverse Assignment Strategies into DETRs
Yiwei Zhang, Jin Gao, Hanshi Wang +4
Label assignment is a critical component in object detectors, particularly within DETR-style frameworks where the one-to-one matching strategy, despite its end-to-end elegance, suf…
Online Segment Any 3D Thing as Instance Tracking
Hanshi Wang, Zijian Cai, Jin Gao +4
Online, real-time, and fine-grained 3D segmentation constitutes a fundamental capability for embodied intelligent agents to perceive and comprehend their operational environments.…
AutoPrune: Each Complexity Deserves a Pruning Policy
Hanshi Wang, Yuhao Xu, Zekun Xu +5
The established redundancy in visual tokens within large vision-language models allows pruning to effectively reduce their substantial computational demands. Previous methods typic…
Towards a deeper GCN: Alleviate over-smoothing with iterative training and fine-tuning
Furong Peng, Jinzhen Gao, Xuan Lu +3
Graph Convolutional Networks (GCNs) suffer from severe performance degradation in deep architectures due to over-smoothing. While existing studies primarily attribute the over-smoo…