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/TransAgg (Laion-CIR-Combined)

TransAgg (Laion-CIR-Combined)

Reported on 8 benchmarks across 2 tasks · 1 paper · 6 SOTA

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

Computer Vision8 results

  • Image RetrievalonCIRR
    R@1· 2023-06-12
    37.87
    best: 50.43 (CoVR-BLIP-2)
    SOTA
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Image RetrievalonCIRR
    R@5· 2023-06-12
    68.88
    best: 81.08 (CoVR-BLIP-2)
    SOTA
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Image RetrievalonCIRR
    R@50· 2023-06-12
    93.86
    best: 96.1 (CoVR-BLIP-2)
    SOTA
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Composed Image Retrieval (CoIR)onCIRR
    R@1· 2023-06-12
    37.87
    best: 50.43 (CoVR-BLIP-2)
    SOTA
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Composed Image Retrieval (CoIR)onCIRR
    R@5· 2023-06-12
    68.88
    best: 81.08 (CoVR-BLIP-2)
    SOTA
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Composed Image Retrieval (CoIR)onCIRR
    R@50· 2023-06-12
    93.86
    best: 96.1 (CoVR-BLIP-2)
    SOTA
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Image RetrievalonFashion IQ
    (Recall@10+Recall@50)/2· 2023-06-12
    44.75
    best: 71.77 (DQU-CIR)
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272
  • Composed Image Retrieval (CoIR)onFashion IQ
    (Recall@10+Recall@50)/2· 2023-06-12
    44.75
    best: 60.57 (CoVR-BLIP-2)
    Zero-shot Composed Text-Image RetrievalarXiv:2306.07272