AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval

Open paper
Benchmark Model Rank Results
image-retrieval-on-google-landmarks-datasetAMES#1mAP@100: 37.8
image-retrieval-on-roxford-hardAMES#2mAP: 80
image-retrieval-on-roxford-mediumAMES#1mAP: 90.7
image-retrieval-on-rparis-hardAMES#1mAP: 89.7
image-retrieval-on-rparis-mediumAMES#1mAP: 94.9

Rank counts only results with a code link.