Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining

Chao Wang, Ehsan Nezhadarya, Tanmana Sadhu, Shengdong Zhang


Abstract
Compositional image retrieval (CIR) is a challenging retrieval task, where the query is composed of a reference image and a modification text, and the target is another image reflecting the modification to the reference image. Due to the great success of the pre-trained vision-and-language model CLIP and its favorable applicability to large-scale retrieval tasks, we propose a CIR model HyCoLe-HNM with CLIP as the backbone. In HyCoLe-HNM, we follow the contrastive pre-training method of CLIP to perform cross-modal representation learning. On this basis, we propose a hybrid compositional learning mechanism, which includes both image compositional learning and text compositional learning. In hybrid compositional learning, we borrow a gated fusion mechanism from a question answering model to perform compositional fusion, and propose a heuristic negative mining method to filter negative samples. Privileged information in the form of image-related texts is utilized in cross-modal representation learning and hybrid compositional learning. Experimental results show that HyCoLe-HNM achieves state-of-the-art performance on three CIR datasets, namely FashionIQ, Fashion200K, and MIT-States.
Anthology ID:
2022.findings-emnlp.92
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1273–1285
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.92
DOI:
10.18653/v1/2022.findings-emnlp.92
Bibkey:
Cite (ACL):
Chao Wang, Ehsan Nezhadarya, Tanmana Sadhu, and Shengdong Zhang. 2022. Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 1273–1285, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining (Wang et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/2022.findings-emnlp.92.pdf
Video:
 https://preview.aclanthology.org/landing_page/2022.findings-emnlp.92.mp4