%0 Conference Proceedings %T ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension %A Subramanian, Sanjay %A Merrill, William %A Darrell, Trevor %A Gardner, Matt %A Singh, Sameer %A Rohrbach, Anna %Y Muresan, Smaranda %Y Nakov, Preslav %Y Villavicencio, Aline %S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) %D 2022 %8 May %I Association for Computational Linguistics %C Dublin, Ireland %F subramanian-etal-2022-reclip %X Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are useful for image classification across domains, it remains unclear if they can be applied in a zero-shot manner to more complex tasks like ReC. We present ReCLIP, a simple but strong zero-shot baseline that repurposes CLIP, a state-of-the-art large-scale model, for ReC. Motivated by the close connection between ReC and CLIP’s contrastive pre-training objective, the first component of ReCLIP is a region-scoring method that isolates object proposals via cropping and blurring, and passes them to CLIP. However, through controlled experiments on a synthetic dataset, we find that CLIP is largely incapable of performing spatial reasoning off-the-shelf. We reduce the gap between zero-shot baselines from prior work and supervised models by as much as 29% on RefCOCOg, and on RefGTA (video game imagery), ReCLIP’s relative improvement over supervised ReC models trained on real images is 8%. %R 10.18653/v1/2022.acl-long.357 %U https://aclanthology.org/2022.acl-long.357 %U https://doi.org/10.18653/v1/2022.acl-long.357 %P 5198-5215