CVNov 24, 2024

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

arXiv:2411.15736v11 citationsh-index: 2Has CodeICASSP
Originality Incremental advance
AI Analysis

This addresses a specific bottleneck in few-shot OOD detection for computer vision, representing an incremental improvement.

The paper tackles the problem of gradient conflict between in-distribution classification and out-of-distribution regularization in few-shot OOD detection, achieving great performance on the ImageNet benchmark.

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.

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