Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval

About

Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification. While supervised CIR relies on costly triplets, Zero-Shot CIR (ZS-CIR) alleviates this reliance through proxy tasks trained on image-text pairs. However, existing proxy tasks primarily enhance visual and textual representations to accommodate a predefined composition mechanism such as pseudo-word injection into a frozen text encoder or linear feature arithmetic. As a result, the composition function itself remains unlearned, limiting the model's ability to express diverse and fine-grained semantic modifications. To address this, we propose FoCo, which models composition as two coordinated stages: focusing on modification-relevant visual content, and then completing the target semantics. We realize these through two proxy tasks: text-anchored visual aggregation to selectively gather visual content guided by localized textual semantics, and context-conditioned semantic completion to transform these aggregated visuals with the remaining scene context into a coherent composed representation. The tasks are trained jointly with a cross-instance contrastive objective, encouraging semantic diversity and discouraging shortcut composition strategies. Extensive experiments on four ZS-CIR benchmarks show FoCo's state-of-the-art performance and improved generalization.

Jingjing Zhang, Lei Zhang, Zheren Fu, Zhendong Mao• 2026

Related benchmarks

TaskDatasetResultRank
Composed Image RetrievalCIRR (test)
Recall@138.5
887
Composed Image RetrievalFashionIQ (val)
Average Recall@1049.1
653
Composed Image RetrievalCIRCO (test)
mAP@1027
432
Zero-Shot Composed Image RetrievalGeneCIS
Focus Recall@118.4
9
Showing 4 of 4 rows

Other info

Follow for update