CVJun 2, 2023

LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning

arXiv:2306.01293v3145 citationsh-index: 52Has Code
Originality Highly original
AI Analysis

This addresses the problem of detecting unseen classes in vision tasks with limited labeled data, offering a novel approach for few-shot OOD detection.

The paper tackles few-shot out-of-distribution (OOD) detection by introducing LoCoOp, a prompt learning method that uses local features from CLIP for OOD regularization, achieving superior performance on ImageNet benchmarks and outperforming zero-shot and fully supervised methods even with one label per class.

We present a novel vision-language prompt learning approach for few-shot out-of-distribution (OOD) detection. Few-shot OOD detection aims to detect OOD images from classes that are unseen during training using only a few labeled in-distribution (ID) images. While prompt learning methods such as CoOp have shown effectiveness and efficiency in few-shot ID classification, they still face limitations in OOD detection due to the potential presence of ID-irrelevant information in text embeddings. To address this issue, we introduce a new approach called Local regularized Context Optimization (LoCoOp), which performs OOD regularization that utilizes the portions of CLIP local features as OOD features during training. CLIP's local features have a lot of ID-irrelevant nuisances (e.g., backgrounds), and by learning to push them away from the ID class text embeddings, we can remove the nuisances in the ID class text embeddings and enhance the separation between ID and OOD. Experiments on the large-scale ImageNet OOD detection benchmarks demonstrate the superiority of our LoCoOp over zero-shot, fully supervised detection methods and prompt learning methods. Notably, even in a one-shot setting -- just one label per class, LoCoOp outperforms existing zero-shot and fully supervised detection methods. The code will be available via https://github.com/AtsuMiyai/LoCoOp.

Code Implementations2 repos
Foundations

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

Your Notes