Inhibited Self-Attention: Sharpening Focus in Vision Transformers
Vision Transformers (ViTs) have demonstrated remarkable performance in computer vision tasks. However, their self-attention mechanism often diffuses focus across background regions, relying on spurious correlations rather than object-relevant cues. Inspired by inhibitory mechanisms observed in biological vision systems, we propose the Inhibited Self-Attention (ISA), a novel self-attention that integrates inhibitory signals to enhance feature selectivity and suppress spurious responses. In contrast to conventional self-attention, which relies solely on positive attention values due to softmax n
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%lucidrains/poly-attention →
- PossiblePossibly related (embedding) · 50%Attention →
- PossiblePossibly related (embedding) · 50%Transformers in Deep Learning: How Self-Attention Changed Modern AI - Snowflake →
- PossiblePossibly related (embedding) · 49%attention-zoo →
- FuzzySimilar title/name (fuzzy) · 59%VioletVision-3B →
“Fuzzy title match (0.73): “Inhibited Self-Attention: Sharpening Focus in Vision Transfo” ≈ “VioletVision-3B””
- LinkedLinked via arxiv author · 85%Peter R. D. van der Wal →
“Inhibited Self-Attention: Sharpening Focus in Vision Transformers”
- LinkedLinked via arxiv author · 85%Nicola Strisciuglio →
“Inhibited Self-Attention: Sharpening Focus in Vision Transformers”
- LinkedLinked via arxiv author · 85%George Azzopardi →
“Inhibited Self-Attention: Sharpening Focus in Vision Transformers”