| | 71.77 | 61.97 | DQU-CIR | |
| TMCIR: Token Merge Benefits Composed Image Retrieval | | 66.56 | 56.57 | TMCIR | 2025-04-15 |
| Improving Composed Image Retrieval via Contrastive Learning with Scaling Positives and Negatives | ✓ Link | 66.41 | 56.37 | SPN4CIR (SPRC) | 2024-04-17 |
| FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval | | 65.97 | | FashionBLIP-2 | 2025-07-08 |
| Sentence-level Prompts Benefit Composed Image Retrieval | ✓ Link | 64.85 | 54.92 | SPRC | 2023-10-09 |
| Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder | ✓ Link | 62.15 | 51.17 | Candidate Set Re-ranking | 2023-05-25 |
| Ranking-aware Uncertainty for Text-guided Image Retrieval | | 61.32 | | RUTIR (BLIP B/16) | 2023-08-16 |
| Data Roaming and Quality Assessment for Composed Image Retrieval | ✓ Link | 59.73 | 48.79 | CASE | 2023-03-16 |
| CaLa: Complementary Association Learning for Augmenting Composed Image Retrieval | ✓ Link | 57.96 | 46.69 | CaLa | 2024-05-29 |
| Bi-directional Training for Composed Image Retrieval via Text Prompt Learning | ✓ Link | 55.4 | | BLIP4CIR+Bi | 2023-03-29 |
| Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features | ✓ Link | 55.36 | | CLIP4Cir (v3) | 2023-08-22 |
| Ranking-aware Uncertainty for Text-guided Image Retrieval | | 55.27 | | RUTIR (CLIP ResNet50) | 2023-08-16 |
| Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations | | 51.34 | | Css-Net | 2023-06-03 |
| Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization | ✓ Link | 50.61 | | MUR (4*ResNet50) | 2022-11-14 |
| Conditioned and Composed Image Retrieval Combining and Partially Fine-Tuning CLIP-Based Features | ✓ Link | 50.03 | | CLIP4Cir (v2) | 2022-06-19 |
| Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization | ✓ Link | 47.28 | | MUR | 2022-11-14 |
| Effective Conditioned and Composed Image Retrieval Combining CLIP-Based Features | ✓ Link | 47.21 | | CLIP4Cir | 2022-01-01 |
| MegaPairs: Massive Data Synthesis For Universal Multimodal Retrieval | ✓ Link | 46.1 | 35.6 | MMRet-MLLM | 2024-12-19 |
| RTIC: Residual Learning for Text and Image Composition using Graph Convolutional Network | ✓ Link | 40.64 | | RTIC-GCN | 2021-04-07 |
| CoSMo: Content-Style Modulation for Image Retrieval With Text Feedback | ✓ Link | 39.45 | | CoSMo | 2021-06-19 |
| CurlingNet: Compositional Learning between Images and Text for Fashion IQ Data | ✓ Link | 38.45 | | CurlingNet | 2020-03-27 |
| Image Search With Text Feedback by Visiolinguistic Attention Learning | ✓ Link | 35.38 | | VAL w/ GloVe | 2020-06-01 |
| Compositional Learning of Image-Text Query for Image Retrieval | ✓ Link | 20.6 | | ComposeAE | 2020-06-19 |
| Learning Sample-wise Rank-Aware Interpolation Weights for Composed Visual Data Retrieval | | | 49.26 | SRAIN | 2026-08-23 |
| Adapting In-context Generation for Enhanced Composed Image Retrieval | ✓ Link | | 55.07 | DAIG (Ours) + SPRC | 2026-06-03 |