Triplet Synthesis For Enhancing Composed Image Retrieval via Counterfactual Image Generation
This addresses the need for efficient dataset construction in CIR, offering a scalable solution to reduce manual effort, though it is incremental as it builds on existing CIR frameworks.
The paper tackles the problem of labor-intensive manual annotation for training Composed Image Retrieval (CIR) models by proposing a novel triplet synthesis method using counterfactual image generation, which automatically generates diverse training triplets and improves CIR model performance.
Composed Image Retrieval (CIR) provides an effective way to manage and access large-scale visual data. Construction of the CIR model utilizes triplets that consist of a reference image, modification text describing desired changes, and a target image that reflects these changes. For effectively training CIR models, extensive manual annotation to construct high-quality training datasets, which can be time-consuming and labor-intensive, is required. To deal with this problem, this paper proposes a novel triplet synthesis method by leveraging counterfactual image generation. By controlling visual feature modifications via counterfactual image generation, our approach automatically generates diverse training triplets without any manual intervention. This approach facilitates the creation of larger and more expressive datasets, leading to the improvement of CIR model's performance.