Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization

TL;DR

This paper introduces GaCoOp, a method that reduces gradient conflicts in few-shot OOD detection by decomposing and projecting gradients, leading to improved performance on large-scale benchmarks.

Contribution

GaCoOp is a novel approach that mitigates gradient conflicts in few-shot OOD detection through gradient decomposition and projection, enhancing detection accuracy.

Findings

Effective in reducing gradient conflicts.

Achieves state-of-the-art performance on ImageNet OOD benchmark.

Improves few-shot OOD detection accuracy.

Abstract

Few-shot out-of-distribution (OOD) detection aims to detect OOD images from unseen classes with only a few labeled in-distribution (ID) images. To detect OOD images and classify ID samples, prior methods have been proposed by regarding the background regions of ID samples as the OOD knowledge and performing OOD regularization and ID classification optimization. However, the gradient conflict still exists between ID classification optimization and OOD regularization caused by biased recognition. To address this issue, we present Gradient Aligned Context Optimization (GaCoOp) to mitigate this gradient conflict. Specifically, we decompose the optimization gradient to identify the scenario when the conflict occurs. Then we alleviate the conflict in inner ID samples and optimize the prompts via leveraging gradient projection. Extensive experiments over the large-scale ImageNet OOD detection benchmark demonstrate that our GaCoOp can effectively mitigate the conflict and achieve great performance. Code will be available at https://github.com/BaoshunWq/ood-GaCoOp.