Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
One Hundred Neural Networks and Brains Watching Videos: Lessons from Alignment
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-194
Temporal modeling in video models drives representational alignment to early visual cortex, while action classification task drives alignment to late brain areas
IC-195
Transformers achieve high brain alignment in early visual cortex at much shallower network depth than CNNs
IC-196
Models trained on Something-Something-V2 (which contains no faces) show reduced alignment with face-selective FFA compared to the same models trained on Kinetics-400
IC-197
Model computational complexity (FLOPs) shows a significant negative correlation with brain alignment in high-level brain areas