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/CoLLM (Pretrained - BLIP-L/16)

CoLLM (Pretrained - BLIP-L/16)

Reported on 18 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 Vision18 results

  • Image RetrievalonFashion IQ
    (Recall@10+Recall@50)/2· 2025-03-25
    45.3
    best: 71.77 (DQU-CIR)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonFashion IQ
    R@10· 2025-03-25
    34.6
    best: 49.96 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonFashion IQ
    R@50· 2025-03-25
    56
    best: 71.17 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonCIRCO
    MAP@5· 2025-03-25
    19.7
    best: 28.36 (ImageScope (CLIP-ViT-L/14))
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonCIRCO
    mAP@10· 2025-03-25
    20.4
    best: 43.4 (MMRet-MLLM)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonCIRCO
    mAP@50· 2025-03-25
    23.1
    best: 31.88 (ImageScope (CLIP-ViT-L/14))
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonCIRR
    R@1· 2025-03-25
    35
    best: 50.43 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonCIRR
    R@10· 2025-03-25
    78.6
    best: 84.7 (CoLLM (finetuned - BLIP-L/16))
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Image RetrievalonCIRR
    R@50· 2025-03-25
    94.2
    best: 96.1 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onFashion IQ
    (Recall@10+Recall@50)/2· 2025-03-25
    45.3
    best: 60.57 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onFashion IQ
    R@10· 2025-03-25
    34.6
    best: 49.96 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onFashion IQ
    R@50· 2025-03-25
    56
    best: 71.17 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onCIRCO
    MAP@5· 2025-03-25
    19.7
    best: 28.36 (ImageScope (CLIP-ViT-L/14))
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onCIRCO
    mAP@10· 2025-03-25
    20.4
    best: 43.4 (MMRet-MLLM)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onCIRCO
    mAP@50· 2025-03-25
    23.1
    best: 31.88 (ImageScope (CLIP-ViT-L/14))
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onCIRR
    R@1· 2025-03-25
    35
    best: 50.43 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onCIRR
    R@10· 2025-03-25
    78.6
    best: 84.7 (CoLLM (finetuned - BLIP-L/16))
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910
  • Composed Image Retrieval (CoIR)onCIRR
    R@50· 2025-03-25
    94.2
    best: 96.1 (CoVR-BLIP-2)
    CoLLM: A Large Language Model for Composed Image RetrievalarXiv:2503.19910