UNICOM-ViT-B-16-512px

Reported on 2 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.

Computer Vision2 results

Image RetrievalonGoogle Landmarks Dataset v2 (retrieval, testing)
mAP@100· 2023-04-12
35.7
best: 37.8 (AMES)
Unicom: Universal and Compact Representation Learning for Image Retrieval arXiv:2304.05884
Image RetrievalonGoogle Landmarks Dataset v2 (retrieval, validation)
mAP@100· 2023-04-12
32.4
best: 33.1 (UNICOM-ViT-L-14-512px)
Unicom: Universal and Compact Representation Learning for Image Retrieval arXiv:2304.05884