Composed Image Retrieval on M-FashionIQ
45.74Dresses Recall@10TEMA
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| TEMAText Encoder=BLIP2026.04 | 45.74 | 69.48 | 50.35 | 71.26 | 55.67 | 75.52 | 50.59 | 72.09 | |
| CandidateText Encoder=BLIP2026.04 | 43.3 | 65.36 | 47.96 | 65.53 | 50.87 | 69.23 | 47.38 | 66.71 | |
| BLIP4CIR+BiText Encoder=BLIP2026.04 | 41.51 | 63.23 | 37.51 | 57.92 | 43.32 | 65 | 40.78 | 62.05 | |
| BLIP4CIRText Encoder=BLIP2026.04 | 40.97 | 63.28 | 37.81 | 59.1 | 44.19 | 64.94 | 40.99 | 62.44 | |
| Text+ImageText Encoder=BLIP2026.04 | 38.96 | 60.57 | 34.48 | 56.39 | 41.5 | 63.13 | 38.31 | 60.03 | |
| FashionSAPText Encoder=ALBEF2026.04 | 25.63 | 51.81 | 26.89 | 51.82 | 32.33 | 59.97 | 28.28 | 54.53 | |
| Text-onlyText Encoder=BLIP2026.04 | 24.72 | 47.94 | 26.88 | 49.67 | 27.25 | 50.22 | 26.28 | 49.28 | |
| FashionViLText Encoder=BERT2026.04 | 22.07 | 47.81 | 22.32 | 46.93 | 29.08 | 55.62 | 24.49 | 50.12 | |
| MGURText Encoder=RoBERTa2026.04 | 21.42 | 45.27 | 16.58 | 37.59 | 23.92 | 49.16 | 20.64 | 44.01 | |
| CLVC-NetText Encoder=LSTM2026.04 | 14.86 | 27.55 | 16.18 | 31.05 | 17.14 | 34.27 | 16.06 | 30.96 | |
| TIRGText Encoder=LSTM2026.04 | 7.88 | 14.35 | 9.66 | 18.3 | 10.07 | 21.51 | 9.2 | 18.05 |