CVAILGNov 26, 2023

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

arXiv:2311.15243v347 citationsh-index: 14Has Code
Originality Incremental advance
AI Analysis

This work addresses the challenge of detecting subtle OOD samples in image datasets with limited data, offering an incremental improvement over existing methods.

The paper tackles the problem of few-shot out-of-distribution (OOD) detection by focusing on challenging ID-like OOD samples, proposing a framework that uses CLIP to discover these outliers and learns prompts, resulting in a 12.16% reduction in FPR95 and 2.76% improvement in AUROC on ImageNet-1k compared to state-of-the-art methods.

Out-of-distribution (OOD) detection methods often exploit auxiliary outliers to train model identifying OOD samples, especially discovering challenging outliers from auxiliary outliers dataset to improve OOD detection. However, they may still face limitations in effectively distinguishing between the most challenging OOD samples that are much like in-distribution (ID) data, i.e., \idlike samples. To this end, we propose a novel OOD detection framework that discovers \idlike outliers using CLIP \cite{DBLP:conf/icml/RadfordKHRGASAM21} from the vicinity space of the ID samples, thus helping to identify these most challenging OOD samples. Then a prompt learning framework is proposed that utilizes the identified \idlike outliers to further leverage the capabilities of CLIP for OOD detection. Benefiting from the powerful CLIP, we only need a small number of ID samples to learn the prompts of the model without exposing other auxiliary outlier datasets. By focusing on the most challenging \idlike OOD samples and elegantly exploiting the capabilities of CLIP, our method achieves superior few-shot learning performance on various real-world image datasets (e.g., in 4-shot OOD detection on the ImageNet-1k dataset, our method reduces the average FPR95 by 12.16\% and improves the average AUROC by 2.76\%, compared to state-of-the-art methods). Code is available at https://github.com/ycfate/ID-like.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes