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.

SotA/Computer Vision/Composed Image Retrieval (CoIR)/Fashion IQ

Composed Image Retrieval (CoIR) on Fashion IQ

Metric: R@50 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕R@50▼Extra DataPaperDate↕Code
1CoVR-BLIP-271.17NoCoVR-2: Automatic Data Construction for Composed...2023-08-28Code
2CoLLM (finetuned - BLIP-L/16)60.7NoCoLLM: A Large Language Model for Composed Image...2025-03-25Code
3SCOT (WACV 2025)60.03NoSCOT: Self-Supervised Contrastive Pretraining Fo...2025-01-12-
4CoVR-BLIP-258.44NoCoVR-2: Automatic Data Construction for Composed...2023-08-28Code
5MagicLens (CoCa L)58.2NoMagicLens: Self-Supervised Image Retrieval with ...2024-03-28Code
6CoLLM (Pretrained - BLIP-L/16)56NoCoLLM: A Large Language Model for Composed Image...2025-03-25Code
7MagicLens (CLIP L)52.5NoMagicLens: Self-Supervised Image Retrieval with ...2024-03-28Code
8ImageScope (CLIP-ViT-L/14)50.78NoImageScope: Unifying Language-Guided Image Retri...2025-03-13Code
9CoLLM (Pretrained - CLIP-L/14)49.5NoCoLLM: A Large Language Model for Composed Image...2025-03-25Code