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/Methodology/16k/OVAD-Box benchmark

16k on OVAD-Box benchmark

Metric: mean average precision (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mean average precision▼AugmentationsPaperDate↕Code
1X-VLM28YesMulti-Grained Vision Language Pre-Training: Alig...2021-11-16Code
2BLIP 2 (pretrained)25.5YesBLIP-2: Bootstrapping Language-Image Pre-trainin...2023-01-30Code
3BLIP24.3YesBLIP: Bootstrapping Language-Image Pre-training ...2022-01-28Code
4OVAD-Baseline-Box21.4NoOpen-vocabulary Attribute Detection2022-11-23Code
5ALBEF21YesAlign before Fuse: Vision and Language Represent...2021-07-16Code
6Open CLIP ViT-B3217YesReproducible scaling laws for contrastive langua...2022-12-14Code
7CLIP VIT-B1616.6YesLearning Transferable Visual Models From Natural...2021-02-26Code