FeatUp (JBU)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology3 results

Representation LearningonImageNet
ADCC· 2024-03-15
64.3
best: 73.3 (JAFAR)
SOTA
FeatUp: A Model-Agnostic Framework for Features at Any Resolution arXiv:2403.10516
Representation LearningonImageNet
Average Drop· 2024-03-15
15.3
best: 66.9 (LiFT)
FeatUp: A Model-Agnostic Framework for Features at Any Resolution arXiv:2403.10516
Representation LearningonImageNet
Average Increase· 2024-03-15
24
best: 32.7 (SAPA)
FeatUp: A Model-Agnostic Framework for Features at Any Resolution arXiv:2403.10516