@inproceedings{wang-etal-2022-exploring,
    title = "Exploring Compositional Image Retrieval with Hybrid Compositional Learning and Heuristic Negative Mining",
    author = "Wang, Chao  and
      Nezhadarya, Ehsan  and
      Sadhu, Tanmana  and
      Zhang, Shengdong",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.findings-emnlp.92/",
    doi = "10.18653/v1/2022.findings-emnlp.92",
    pages = "1273--1285",
    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."
}