TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection

TL;DR

TagFog introduces a novel framework that uses textual anchors from ChatGPT and fake OOD data to enhance visual out-of-distribution detection, achieving state-of-the-art results.

Contribution

The paper presents a new learning framework combining textual semantic anchors and fake OOD data to improve OOD detection performance.

Findings

Achieved state-of-the-art results on multiple benchmarks.

Effective use of textual embeddings from ChatGPT for OOD detection.

Flexible framework compatible with existing post-hoc methods.

Abstract

Out-of-distribution (OOD) detection is crucial in many real-world applications. However, intelligent models are often trained solely on in-distribution (ID) data, leading to overconfidence when misclassifying OOD data as ID classes. In this study, we propose a new learning framework which leverage simple Jigsaw-based fake OOD data and rich semantic embeddings (`anchors') from the ChatGPT description of ID knowledge to help guide the training of the image encoder. The learning framework can be flexibly combined with existing post-hoc approaches to OOD detection, and extensive empirical evaluations on multiple OOD detection benchmarks demonstrate that rich textual representation of ID knowledge and fake OOD knowledge can well help train a visual encoder for OOD detection. With the learning framework, new state-of-the-art performance was achieved on all the benchmarks. The code is available at \url{https://github.com/Cverchen/TagFog}.