Css-Net

Reported on 4 benchmarks across 2 tasks · 1 paper · 1 SOTA

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

Miscellaneous3 results

Image Retrieval with Multi-Modal QueryonFashion200k
Recall@1· 2023-06-03
23.4
SOTA
Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations arXiv:2306.02092
Image Retrieval with Multi-Modal QueryonFashion200k
Recall@10· 2023-06-03
52
best: 55.3 (ComposeAE)
Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations arXiv:2306.02092
Image Retrieval with Multi-Modal QueryonFashion200k
Recall@50· 2023-06-03
72
best: 73.4 (ComposeAE)
Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations arXiv:2306.02092

Computer Vision1 result

Image RetrievalonFashion IQ
(Recall@10+Recall@50)/2· 2023-06-03
51.34
best: 71.77 (DQU-CIR)
Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations arXiv:2306.02092