RegNet

image · discriminative

Findings

• IC-1469Progress on standard ImageNet generalization benchmarks is 2.5x faster than progress on crowdsourced global data (DollarStreet, GEODE) across 98 vision models
• IC-1470Geographic disparities (Europe-Africa accuracy gap) are large across all 98 models and have more than tripled between least and best performing models on DollarStreet
• IC-194Temporal modeling in video models drives representational alignment to early visual cortex, while action classification task drives alignment to late brain areas