2 papers
cs.CV2026
Rényi Attention Entropy for Patch Pruning
Hiroaki Aizawa, Yuki Igaue
Transformers are strong baselines in both vision and language because self-attention captures long-range dependencies across tokens. However, the cost of self-attention grows quadr…
cs.CV2025
Patch Pruning Strategy Based on Robust Statistical Measures of Attention Weight Diversity in Vision Transformers
Yuki Igaue, Hiroaki Aizawa
Multi-head self-attention is a distinctive feature extraction mechanism of vision transformers that computes pairwise relationships among all input patches, contributing significan…