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/FC-CLIP

FC-CLIP

Reported on 8 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision8 results

  • Open Vocabulary Panoptic SegmentationonADE20K
    PQ· 2023-08-04
    26.8
    best: 31.6 (UMG-CLIP-E/14)
    SOTA
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonCityscapes
    mIoU· 2023-08-04
    56.2
    SOTA
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonADE20K-847
    mIoU· 2023-08-04
    14.8
    best: 17.3 (UMG-CLIP-E/14)
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonPascalVOC-20b
    mIoU· 2023-08-04
    81.8
    best: 85.4 (UMG-CLIP-E/14)
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonPASCAL Context-459
    mIoU· 2023-08-04
    18.2
    best: 25.8 (SILC)
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonPascalVOC-20
    mIoU· 2023-08-04
    95.4
    best: 97.9 (UMG-CLIP-L/14)
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonPASCAL Context-59
    mIoU· 2023-08-04
    58.4
    best: 64.6 (HyperSeg)
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487
  • Open Vocabulary Semantic SegmentationonADE20K-150
    mIoU· 2023-08-04
    34.1
    best: 38.2 (Mask-Adapter)
    Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIParXiv:2308.02487