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.

Models/CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)

CenterNet2 (Swin-L w/ X-Paste + Copy-Paste)

Reported on 13 benchmarks across 6 tasks · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology8 results

  • 3DonLVIS v1.0 val
    box AP· 2022-12-07
    50.9
    best: 68 (Co-DETR (single-scale))
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 3DonLVIS v1.0 val
    box APr· 2022-12-07
    48.7
    best: 64 (Grounding DINO 1.5 Pro)
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 2D ClassificationonLVIS v1.0 val
    box AP· 2022-12-07
    50.9
    best: 68 (Co-DETR (single-scale))
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 2D ClassificationonLVIS v1.0 val
    box APr· 2022-12-07
    48.7
    best: 64 (Grounding DINO 1.5 Pro)
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 2D Object DetectiononLVIS v1.0 val
    box AP· 2022-12-07
    50.9
    best: 68 (Co-DETR (single-scale))
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 2D Object DetectiononLVIS v1.0 val
    box APr· 2022-12-07
    48.7
    best: 64 (Grounding DINO 1.5 Pro)
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 16konLVIS v1.0 val
    box AP· 2022-12-07
    50.9
    best: 68 (Co-DETR (single-scale))
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • 16konLVIS v1.0 val
    box APr· 2022-12-07
    48.7
    best: 64 (Grounding DINO 1.5 Pro)
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863

Computer Vision5 results

  • Instance SegmentationonLVIS v1.0 val
    mask APr· 2022-12-07
    43.8
    best: 45.8 (DiverGen (Swin-L))
    SOTA
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • Object DetectiononLVIS v1.0 val
    box AP· 2022-12-07
    50.9
    best: 68 (Co-DETR (single-scale))
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • Object DetectiononLVIS v1.0 val
    box APr· 2022-12-07
    48.7
    best: 64 (Grounding DINO 1.5 Pro)
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • Instance SegmentationonCOCO minival
    mask AP· 2022-12-07
    48.8
    best: 56.6 (Co-DETR)
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863
  • Instance SegmentationonLVIS v1.0 val
    mask AP· 2022-12-07
    45.4
    best: 60.7 (Co-DETR (single-scale))
    X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusionarXiv:2212.03863