2 papers
cs.CV2026
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
Alan Z. Song, Yinjie Chen, Mu Nan +8
Vision Transformers (ViTs) learn rich visual-semantic representations through all-to-all self-attention among patch tokens. However, this design implicitly assumes that direct pair…
cs.CV2024
Paying more attention to local contrast: improving infrared small target detection performance via prior knowledge
Peichao Wang, Jiabao Wang, Yao Chen +3
The data-driven method for infrared small target detection (IRSTD) has achieved promising results. However, due to the small scale of infrared small target datasets and the limited…