TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detection
This addresses the issue of models overconfidently misclassifying OOD data in real-world applications, representing an incremental improvement through integration with existing methods.
The paper tackles the problem of visual out-of-distribution (OOD) detection by proposing a learning framework that uses ChatGPT-generated textual anchors and fake OOD data to train an image encoder, achieving new state-of-the-art performance on multiple benchmarks.
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}.