TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Computer Vision/Image Retrieval/CREPE (Compositional REPresentation Evaluation)

Image Retrieval on CREPE (Compositional REPresentation Evaluation)

Metric: Recall@1 (HN-Atom + HN-Comp, UC) (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕Recall@1 (HN-Atom + HN-Comp, UC)▼Extra DataPaperDate↕Code
1ViT-L-14 (LAION400M)33.81NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
2ViT-B-16+240 (LAION400M)32.26NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
3ViT-B-16 (LAION400M)30.81NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
4ViT-B-32 (LAION400M)28NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
5RN101 (YFCC15M)20.5NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
6RN50 (YFCC15M)20.08NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
7RN50 (CC12M)19.96NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code
8Random9.09NoCREPE: Can Vision-Language Foundation Models Rea...2022-12-13Code