LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910124181815296 |
|---|---|
| author | ai, Gensmo. Gao, Chao Xue, Siqiao Fu, Jiwen Gu, Tingyi Li, Shanshan Zhou, Fan |
| author_facet | ai, Gensmo. Gao, Chao Xue, Siqiao Fu, Jiwen Gu, Tingyi Li, Shanshan Zhou, Fan |
| contents | In this paper, we present LookBench (We use the term "look" to reflect retrieval that mirrors how people shop -- finding the exact item, a close substitute, or a visually consistent alternative.), a live, holistic and challenging benchmark for fashion image retrieval in real e-commerce settings. LookBench includes both recent product images sourced from live websites and AI-generated fashion images, reflecting contemporary trends and use cases. Each test sample is time-stamped and we intend to update the benchmark periodically, enabling contamination-aware evaluation aligned with declared training cutoffs. Grounded in our fine-grained attribute taxonomy, LookBench covers single-item and outfit-level retrieval across. Our experiments reveal that LookBench poses a significant challenge on strong baselines, with many models achieving below $60\%$ Recall@1. Our proprietary model achieves the best performance on LookBench, and we release an open-source counterpart that ranks second, with both models attaining state-of-the-art results on legacy Fashion200K evaluations. LookBench is designed to be updated semi-annually with new test samples and progressively harder task variants, providing a durable measure of progress. We publicly release our leaderboard, dataset, evaluation code, and trained models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_14706 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval ai, Gensmo. Gao, Chao Xue, Siqiao Fu, Jiwen Gu, Tingyi Li, Shanshan Zhou, Fan Computer Vision and Pattern Recognition In this paper, we present LookBench (We use the term "look" to reflect retrieval that mirrors how people shop -- finding the exact item, a close substitute, or a visually consistent alternative.), a live, holistic and challenging benchmark for fashion image retrieval in real e-commerce settings. LookBench includes both recent product images sourced from live websites and AI-generated fashion images, reflecting contemporary trends and use cases. Each test sample is time-stamped and we intend to update the benchmark periodically, enabling contamination-aware evaluation aligned with declared training cutoffs. Grounded in our fine-grained attribute taxonomy, LookBench covers single-item and outfit-level retrieval across. Our experiments reveal that LookBench poses a significant challenge on strong baselines, with many models achieving below $60\%$ Recall@1. Our proprietary model achieves the best performance on LookBench, and we release an open-source counterpart that ranks second, with both models attaining state-of-the-art results on legacy Fashion200K evaluations. LookBench is designed to be updated semi-annually with new test samples and progressively harder task variants, providing a durable measure of progress. We publicly release our leaderboard, dataset, evaluation code, and trained models. |
| title | LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.14706 |