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/ConvNeXt-B

ConvNeXt-B

Reported on 12 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.

Methodology3 results

  • Domain AdaptationonVizWiz-Classification
    Accuracy - All Images· uses extra data· 2022-01-10
    53.5
    best: 57.2 (VOLO-D5)
    A ConvNet for the 2020sarXiv:2201.03545
  • Domain AdaptationonVizWiz-Classification
    Accuracy - Clean Images· uses extra data· 2022-01-10
    56
    best: 450 (ViT-8/B-224)
    A ConvNet for the 2020sarXiv:2201.03545
  • Domain AdaptationonVizWiz-Classification
    Accuracy - Corrupted Images· uses extra data· 2022-01-10
    46.9
    best: 51.8 (VOLO-D5)
    A ConvNet for the 2020sarXiv:2201.03545

Medical3 results

  • Semantic SegmentationonADE20K
    GFLOPs (512 x 512)· 2022-01-10
    1170
    best: 3335 (ConvNeXt-XL++)
    A ConvNet for the 2020sarXiv:2201.03545
  • Semantic SegmentationonADE20K
    Params (M)· 2022-01-10
    122
    best: 3000 (FD-SwinV2-G)
    A ConvNet for the 2020sarXiv:2201.03545
  • Semantic SegmentationonADE20K
    Validation mIoU· 2022-01-10
    49.9
    best: 63.6 (ViT-P (InternImage-H))
    A ConvNet for the 2020sarXiv:2201.03545

Computer Vision3 results

  • Domain GeneralizationonVizWiz-Classification
    Accuracy - All Images· uses extra data· 2022-01-10
    53.5
    best: 57.2 (VOLO-D5)
    A ConvNet for the 2020sarXiv:2201.03545
  • Domain GeneralizationonVizWiz-Classification
    Accuracy - Clean Images· uses extra data· 2022-01-10
    56
    best: 450 (ViT-8/B-224)
    A ConvNet for the 2020sarXiv:2201.03545
  • Domain GeneralizationonVizWiz-Classification
    Accuracy - Corrupted Images· uses extra data· 2022-01-10
    46.9
    best: 51.8 (VOLO-D5)
    A ConvNet for the 2020sarXiv:2201.03545

Audio3 results

  • 10-shot image generationonADE20K
    GFLOPs (512 x 512)· 2022-01-10
    1170
    best: 3335 (ConvNeXt-XL++)
    A ConvNet for the 2020sarXiv:2201.03545
  • 10-shot image generationonADE20K
    Params (M)· 2022-01-10
    122
    best: 3000 (FD-SwinV2-G)
    A ConvNet for the 2020sarXiv:2201.03545
  • 10-shot image generationonADE20K
    Validation mIoU· 2022-01-10
    49.9
    best: 63.6 (ViT-P (InternImage-H))
    A ConvNet for the 2020sarXiv:2201.03545