Dissecting Query-Key Interaction in Vision Transformers
–Neural Information Processing Systems
Self-attention in vision transformers is often thought to perform perceptual grouping where tokens attend to other tokens with similar embeddings, which could correspond to semantically similar features of an object.
Neural Information Processing Systems
Oct-10-2025, 04:21:00 GMT
- Country:
- North America
- Dominican Republic (0.04)
- United States
- Canada > Ontario
- Toronto (0.04)
- Europe > United Kingdom
- England > Oxfordshire > Oxford (0.04)
- Asia > China
- Hong Kong (0.04)
- North America
- Genre:
- Research Report
- New Finding (1.00)
- Experimental Study (1.00)
- Research Report
- Industry:
- Health & Medicine > Therapeutic Area > Neurology (0.46)
- Technology: