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/LVIS v1.0 val

16k on LVIS v1.0 val

Metric: box APr (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕box APr▼AugmentationsPaperDate↕Code
1Grounding DINO 1.5 Pro64YesGrounding DINO 1.5: Advance the "Edge" of Open-S...2024-05-16Code
2RichSem (Focal-H + ImageNet as weakly-supervised extra data)61.2YesLearning from Rich Semantics and Coarse Location...2023-10-18Code
3EVA55.1YesEVA: Exploring the Limits of Masked Visual Repre...2022-11-14Code
4DiverGen (Swin-L)50.1NoDiverGen: Improving Instance Segmentation by Lea...2024-05-16Code
5CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)48.7NoX-Paste: Revisiting Scalable Copy-Paste for Inst...2022-12-07Code
6SimLTD Fully Supervised (Swin-L)42.4NoSimLTD: Simple Supervised and Semi-Supervised Lo...2024-12-28Code