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/Context-I2W

Context-I2W

Reported on 8 benchmarks across 2 tasks · 1 paper

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

Computer Vision8 results

  • Image RetrievalonImageNet
    Average Recall· 2023-09-28
    20.25
    best: 24.46 (iSEARLE-XL (CLIP L/14))
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Image RetrievalonCIRCO
    mAP@10· 2023-09-28
    14.62
    best: 43.4 (MMRet-MLLM)
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Image RetrievalonCOCO (Common Objects in Context)
    Actions Recall@5· 2023-09-28
    28.5
    best: 32.55 (iSEARLE-XL-OTI (CLIP L/14))
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Image RetrievalonImageNet-R
    (Recall@10+Recall@50)/2· 2023-09-28
    20.25
    best: 52.95 (MagicLens (CoCa L))
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Composed Image Retrieval (CoIR)onImageNet
    Average Recall· 2023-09-28
    20.25
    best: 24.46 (iSEARLE-XL (CLIP L/14))
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Composed Image Retrieval (CoIR)onCIRCO
    mAP@10· 2023-09-28
    14.62
    best: 43.4 (MMRet-MLLM)
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Composed Image Retrieval (CoIR)onCOCO (Common Objects in Context)
    Actions Recall@5· 2023-09-28
    28.5
    best: 32.55 (iSEARLE-XL-OTI (CLIP L/14))
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137
  • Composed Image Retrieval (CoIR)onImageNet-R
    (Recall@10+Recall@50)/2· 2023-09-28
    20.25
    best: 52.95 (MagicLens (CoCa L))
    Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image RetrievalarXiv:2309.16137