To address the core challenges of the OACIR task, we propose AdaFocal, an effective framework that dynamically modulates visual attention for precise, instance-level retrieval. Our approach augments a multimodal fusion backbone with a lightweight Context-Aware Attention Modulator (CAAM), enabling a nuanced balance between instance fidelity and compositional reasoning.
AdaFocal Framework Overview
Specifically, AdaFocal employs a two-stage reasoning process: Contextual Perception and Adaptive Focus. It first perceives the query's compositional context to predict a modulation scalar (β). This learned signal then drives an Attention Activation Mechanism, which explicitly and adaptively intensifies the visual focus on the user-specified instance region (provided via bounding box) during multimodal feature fusion.
By dynamically re-weighting the attention distribution, AdaFocal seamlessly synthesizes the anchored instance, the global visual scene, and the textual modification into a coherent representation, establishing a robust and flexible baseline for identity-preserving retrieval.
Once downloaded, you can directly evaluate the models using the evaluate.sh script provided in our GitHub codebase. Open evaluate.sh and set the path to your downloaded weights:
bash
1# Inside evaluate.sh2DATASET="Fashion"3MODEL_NAME="oacir_adafocal"4MODEL_WEIGHT="./checkpoints/adafocal_scalar.pt"# or adafocal_vector.pt
Then execute the script:
bash evaluate.sh
🏆 Model Performance on OACIRR
We provide two variants of the AdaFocal weights. You can instantly reproduce the following results using our provided evaluate.sh script.
If you find our dataset, models, or codebase useful in your research, please consider citing our paper:
bibtex
1@inproceedings{yang2026beyond,
2 title={Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval},
3 author={Yang, Yuxin and Zhou, Yinan and Chen, Yuxin and Zhang, Ziqi and Ma, Zongyang and Yuan, Chunfeng and Li, Bing and Gao, Jun and Hu, Weiming},
4 booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
5 pages={31155--31165},
6 year={2026}
7}
