LLM meets Vision-Language Models for Zero-Shot One-Class Classification
This addresses the problem of classifying single categories without example images for researchers in computer vision, though it is incremental as it builds on existing vision-language models.
The paper tackles zero-shot one-class visual classification, where only a label is available for the target class, by proposing a method that uses large language models to identify visually confusing objects and vision-language models like CLIP for classification, achieving outperformance over adapted alternatives on adapted benchmarks.
We consider the problem of zero-shot one-class visual classification, extending traditional one-class classification to scenarios where only the label of the target class is available. This method aims to discriminate between positive and negative query samples without requiring examples from the target class. 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 demonstrate the ability of the proposed method to outperform adapted off-the-shelf alternatives in this setting. Namely, we propose a realistic benchmark where negative query samples are drawn from the same original dataset as positive ones, including a granularity-controlled version of iNaturalist, where negative samples are at a fixed distance in the taxonomy tree from the positive ones. To our knowledge, we are the first to demonstrate the ability to discriminate a single category from other semantically related ones using only its label.