Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT Thomas Y erxa
–Neural Information Processing Systems
"contrastive-equivariant" versions that encourage preservation of input transformations without supervised access to the transformation parameters.
Neural Information Processing Systems
Feb-17-2026, 10:31:15 GMT
- Country:
- North America > United States (0.14)
- South America > Chile
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.93)
- Research Report
- Industry:
- Health & Medicine > Therapeutic Area > Neurology (0.93)
- Technology:
- Information Technology > Artificial Intelligence
- Cognitive Science (1.00)
- Machine Learning
- Inductive Learning (0.83)
- Neural Networks (1.00)
- Representation & Reasoning (0.92)
- Vision (1.00)
- Information Technology > Artificial Intelligence