LLM meets Vision-Language Models for Zero-Shot One-Class Classification

arXiv:2404.00675v1 Announce Type: new
Abstract: We consider the problem of zero-shot one-class visual classification. In this setting, only the label of the target class is available, and the goal is to discriminate between positive and negative query samples without requiring any validation example from the target task. We propose a two-step solution that first queries large language models for visually confusing objects and then relies on vision-language pre-trained models (e.g., CLIP) to perform classification. By adapting large-scale vision benchmarks, we …

abstract arxiv class classification cs.ai cs.cv example language language models llm negative positive query samples solution type validation vision vision-language models visual zero-shot