Zero Shot Composed Image Retrieval
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912418210250752 |
|---|---|
| author | Kakarla, Santhosh Venkata, Gautama Shastry Bulusu |
| author_facet | Kakarla, Santhosh Venkata, Gautama Shastry Bulusu |
| contents | Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text with separate pretrained vision-language encoders, reaches only 20-25\% Recall@10 on the FashionIQ benchmark. We improve this by fine-tuning BLIP-2 with a lightweight Q-Former that fuses visual and textual features into a single embedding, raising Recall@10 to 45.6\% (shirt), 40.1\% (dress), and 50.4\% (top-tee) and increasing the average Recall@50 to 67.6\%. We also examine Retrieval-DPO, which fine-tunes CLIP's text encoder with a Direct Preference Optimization loss applied to FAISS-mined hard negatives. Despite extensive tuning of the scaling factor, index, and sampling strategy, Retrieval-DPO attains only 0.02\% Recall@10 -- far below zero-shot and prompt-tuned baselines -- because it (i) lacks joint image-text fusion, (ii) uses a margin objective misaligned with top-$K$ metrics, (iii) relies on low-quality negatives, and (iv) keeps the vision and Transformer layers frozen. Our results show that effective preference-based CIR requires genuine multimodal fusion, ranking-aware objectives, and carefully curated negatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zero Shot Composed Image Retrieval Kakarla, Santhosh Venkata, Gautama Shastry Bulusu Computer Vision and Pattern Recognition Composed image retrieval (CIR) allows a user to locate a target image by applying a fine-grained textual edit (e.g., ``turn the dress blue'' or ``remove stripes'') to a reference image. Zero-shot CIR, which embeds the image and the text with separate pretrained vision-language encoders, reaches only 20-25\% Recall@10 on the FashionIQ benchmark. We improve this by fine-tuning BLIP-2 with a lightweight Q-Former that fuses visual and textual features into a single embedding, raising Recall@10 to 45.6\% (shirt), 40.1\% (dress), and 50.4\% (top-tee) and increasing the average Recall@50 to 67.6\%. We also examine Retrieval-DPO, which fine-tunes CLIP's text encoder with a Direct Preference Optimization loss applied to FAISS-mined hard negatives. Despite extensive tuning of the scaling factor, index, and sampling strategy, Retrieval-DPO attains only 0.02\% Recall@10 -- far below zero-shot and prompt-tuned baselines -- because it (i) lacks joint image-text fusion, (ii) uses a margin objective misaligned with top-$K$ metrics, (iii) relies on low-quality negatives, and (iv) keeps the vision and Transformer layers frozen. Our results show that effective preference-based CIR requires genuine multimodal fusion, ranking-aware objectives, and carefully curated negatives. |
| title | Zero Shot Composed Image Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.06602 |