English

Waffling around for Performance: Visual Classification with Random Words and Broad Concepts

Computer Vision and Pattern Recognition 2023-08-21 v2 Machine Learning

Abstract

The visual classification performance of vision-language models such as CLIP has been shown to benefit from additional semantic knowledge from large language models (LLMs) such as GPT-3. In particular, averaging over LLM-generated class descriptors, e.g. "waffle, which has a round shape", can notably improve generalization performance. In this work, we critically study this behavior and propose WaffleCLIP, a framework for zero-shot visual classification which simply replaces LLM-generated descriptors with random character and word descriptors. Without querying external models, we achieve comparable performance gains on a large number of visual classification tasks. This allows WaffleCLIP to both serve as a low-cost alternative, as well as a sanity check for any future LLM-based vision-language model extensions. We conduct an extensive experimental study on the impact and shortcomings of additional semantics introduced with LLM-generated descriptors, and showcase how - if available - semantic context is better leveraged by querying LLMs for high-level concepts, which we show can be done to jointly resolve potential class name ambiguities. Code is available here: https://github.com/ExplainableML/WaffleCLIP.

Keywords

Cite

@article{arxiv.2306.07282,
  title  = {Waffling around for Performance: Visual Classification with Random Words and Broad Concepts},
  author = {Karsten Roth and Jae Myung Kim and A. Sophia Koepke and Oriol Vinyals and Cordelia Schmid and Zeynep Akata},
  journal= {arXiv preprint arXiv:2306.07282},
  year   = {2023}
}

Comments

Accepted to ICCV 2023. Main paper with 9 pages

R2 v1 2026-06-28T11:03:12.426Z