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/SEIZE (CLIP G/14)

SEIZE (CLIP G/14)

Reported on 10 benchmarks across 2 tasks

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

Computer Vision10 results

  • Image RetrievalonFashion IQ
    (Recall@10+Recall@50)/2
    54.45
    best: 71.77 (DQU-CIR)
  • Image RetrievalonCIRCO
    mAP@10
    33.77
    best: 43.4 (MMRet-MLLM)
  • Image RetrievalonCIRR
    R@1
    38.87
    best: 50.43 (CoVR-BLIP-2)
  • Image RetrievalonCIRR
    R@10
    79.42
    best: 84.7 (CoLLM (finetuned - BLIP-L/16))
  • Image RetrievalonCIRR
    R@5
    69.42
    best: 81.08 (CoVR-BLIP-2)
  • Composed Image Retrieval (CoIR)onFashion IQ
    (Recall@10+Recall@50)/2
    54.45
    best: 60.57 (CoVR-BLIP-2)
  • Composed Image Retrieval (CoIR)onCIRCO
    mAP@10
    33.77
    best: 43.4 (MMRet-MLLM)
  • Composed Image Retrieval (CoIR)onCIRR
    R@1
    38.87
    best: 50.43 (CoVR-BLIP-2)
  • Composed Image Retrieval (CoIR)onCIRR
    R@10
    79.42
    best: 84.7 (CoLLM (finetuned - BLIP-L/16))
  • Composed Image Retrieval (CoIR)onCIRR
    R@5
    69.42
    best: 81.08 (CoVR-BLIP-2)