-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Jawade_2025_WACV, author = {Jawade, Bhavin and Soares, Jo\~ao V. B. and Thadani, Kapil and Mohan, Deen Dayal and Eshratifar, Amir Erfan and Culpepper, Benjamin and de Juan, Paloma and Setlur, Srirangaraj and Govindaraju, Venu}, title = {SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot Compositional Retrieval}, booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)}, month = {February}, year = {2025}, pages = {5509-5519} }
SCOT: Self-Supervised Contrastive Pretraining for Zero-Shot Compositional Retrieval
Abstract
Compositional image retrieval (CIR) is a multimodal learning task where a model combines a query image with a user-provided text modification to retrieve a target image. CIR finds applications in a variety of domains including product retrieval (e-commerce) and web search. Existing methods primarily focus on fully-supervised learning wherein models are trained on datasets of labeled triplets such as FashionIQ and CIRR. This poses two significant challenges: (i) curating such triplet datasets is labor intensive; and (ii) models lack generalization to unseen objects and domains. In this work we propose SCOT (Self-supervised COmpositional Training) a novel zero-shot compositional pretraining strategy that combines existing large image-text pair datasets with the generative capabilities of large language models to contrastively train an embedding composition network. Specifically we show that the text embedding from a large-scale contrastively-pretrained vision-language model can be utilized as proxy target supervision during compositional pretraining replacing the target image embedding. In zero-shot settings this strategy surpasses SOTA zero-shot compositional retrieval methods as well as many fully-supervised methods on standard benchmarks such as FashionIQ and CIRR.
Related Material