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/OWL-ViT (CLIP-L/14)

OWL-ViT (CLIP-L/14)

Reported on 12 benchmarks across 6 tasks · 1 paper · 6 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
    AP novel-Unrestricted open-vocabulary training· uses extra data· 2022-05-12
    31.2
    best: 45.8 (DITO)
    SOTA
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 2D ClassificationonLVIS v1.0
    AP novel-Unrestricted open-vocabulary training· uses extra data· 2022-05-12
    31.2
    best: 45.8 (DITO)
    SOTA
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 2D Object DetectiononLVIS v1.0
    AP novel-Unrestricted open-vocabulary training· uses extra data· 2022-05-12
    31.2
    best: 45.8 (DITO)
    SOTA
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 16konLVIS v1.0
    AP novel-Unrestricted open-vocabulary training· uses extra data· 2022-05-12
    31.2
    best: 45.8 (DITO)
    SOTA
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 3DonLVIS v1.0
    AP novel-LVIS base training· uses extra data· 2022-05-12
    25.6
    best: 43.4 (LaMI-DETR)
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 2D ClassificationonLVIS v1.0
    AP novel-LVIS base training· uses extra data· 2022-05-12
    25.6
    best: 43.4 (LaMI-DETR)
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 2D Object DetectiononLVIS v1.0
    AP novel-LVIS base training· uses extra data· 2022-05-12
    25.6
    best: 43.4 (LaMI-DETR)
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • 16konLVIS v1.0
    AP novel-LVIS base training· uses extra data· 2022-05-12
    25.6
    best: 43.4 (LaMI-DETR)
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230

Computer Vision4 results

  • Object DetectiononLVIS v1.0
    AP novel-Unrestricted open-vocabulary training· uses extra data· 2022-05-12
    31.2
    best: 45.8 (DITO)
    SOTA
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • Open Vocabulary Object DetectiononLVIS v1.0
    AP novel-Unrestricted open-vocabulary training· uses extra data· 2022-05-12
    31.2
    best: 45.8 (DITO)
    SOTA
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • Object DetectiononLVIS v1.0
    AP novel-LVIS base training· uses extra data· 2022-05-12
    25.6
    best: 43.4 (LaMI-DETR)
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230
  • Open Vocabulary Object DetectiononLVIS v1.0
    AP novel-LVIS base training· uses extra data· 2022-05-12
    25.6
    best: 43.4 (LaMI-DETR)
    Simple Open-Vocabulary Object Detection with Vision TransformersarXiv:2205.06230