Robust and Decomposable Average Precision for Image Retrieval

Open paper
Benchmark Model Rank Results
image-retrieval-on-cub-200-2011ROADMAP (Deit-B)#2R@1: 77.4
image-retrieval-on-cub-200-2011ROADMAP (ResNet-50)#4R@1: 68.5
image-retrieval-on-inaturalistROADMAP (DeiT-S)#4R@1: 73.6R@16: 93.1R@32: 95.2R@5: 86.2
image-retrieval-on-inaturalistROADMAP (ResNet-50)#8R@1: 69.1R@16: 91.3R@32: 93.9R@5: 83.1
image-retrieval-on-sopROADMAP (DeiT-B)#2R@1: 86.0
image-retrieval-on-sopROADMAP (ResNet-50)#4R@1: 83.1
metric-learning-on-stanford-online-products-1ROADMAP (DeiT-S)#5R@1: 86.0
metric-learning-on-stanford-online-products-1ROADMAP (ResNet-50)#9R@1: 83.1

Rank counts only results with a code link.