CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets

Zachary Novack, Saurabh Garg, Zachary Chase Lipton

Keywords: open vocabulary models, CLIP, zero-shot learning, zero-shot image classification

Abstract: Open vocabulary models (e.g. CLIP) have shown strong performance on zeroshot classification through their ability generate embeddings for each class based on their (natural language) names. Prior work has focused on improving the accuracy of these models through prompt engineering or by incorporating a small amount of labeled downstream data (via finetuning). In this paper, we propose Classification with Hierarchical Label Sets (or CHiLS), an alternative strategy that proceeds in three steps: (i) for each class, produce a set of subclasses, using either existing label hierarchies or by querying GPT-3; (ii) perform the standard zero-shot CLIP procedure as though these subclasses were the labels of interest; (iii) map the predicted subclass back to its parent to produce the final prediction. Across numerous datasets, CHiLS leads to improved accuracy yielding gains of over 30% in situations where known hierarchies are available and more modest gains when they are not. CHiLS is simple to implement within existing CLIP pipelines and requires no additional training cost.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2302.02551/code)