ReSFU

Reported on 3 benchmarks across 1 task · 1 paper

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

Methodology3 results

Representation LearningonImageNet
ADCC· 2024-07-02
59.4
best: 73.3 (JAFAR)
A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling arXiv:2407.02283
Representation LearningonImageNet
Average Drop· 2024-07-02
14.5
best: 66.9 (LiFT)
A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling arXiv:2407.02283
Representation LearningonImageNet
Average Increase· 2024-07-02
24
best: 32.7 (SAPA)
A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling arXiv:2407.02283