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/X-Decoder (Davit-d5, Deform, single-scale, 1280x1280)

X-Decoder (Davit-d5, Deform, single-scale, 1280x1280)

Reported on 13 benchmarks across 4 tasks · 1 paper

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

Computer Vision7 results

  • Instance SegmentationonADE20K val
    AP· uses extra data· 2022-12-21
    38.7
    best: 44.2 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Instance SegmentationonADE20K val
    APL· uses extra data· 2022-12-21
    59.6
    best: 64.3 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Instance SegmentationonADE20K val
    APM· uses extra data· 2022-12-21
    43.3
    best: 49.9 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Instance SegmentationonADE20K val
    APS· uses extra data· 2022-12-21
    18.9
    best: 23.7 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Panoptic SegmentationonADE20K val
    AP· uses extra data· 2022-12-21
    38.7
    best: 40.2 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Panoptic SegmentationonADE20K val
    PQ· uses extra data· 2022-12-21
    52.4
    best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Panoptic SegmentationonADE20K val
    mIoU· uses extra data· 2022-12-21
    59.1
    best: 60.4 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270

Medical3 results

  • Semantic SegmentationonADE20K val
    AP· uses extra data· 2022-12-21
    38.7
    best: 40.2 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Semantic SegmentationonADE20K val
    PQ· uses extra data· 2022-12-21
    52.4
    best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • Semantic SegmentationonADE20K val
    mIoU· uses extra data· 2022-12-21
    59.1
    best: 62.8 (BEiT-3)
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270

Audio3 results

  • 10-shot image generationonADE20K val
    AP· uses extra data· 2022-12-21
    38.7
    best: 40.2 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • 10-shot image generationonADE20K val
    PQ· uses extra data· 2022-12-21
    52.4
    best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270
  • 10-shot image generationonADE20K val
    mIoU· uses extra data· 2022-12-21
    59.1
    best: 62.8 (BEiT-3)
    Generalized Decoding for Pixel, Image, and LanguagearXiv:2212.11270