通过梯度对齐优化，提升少样本分布外检测的准确率。
Enhancing Few-Shot Out-of-Distribution Detection with Gradient Aligned Context Optimization
- 分解优化梯度，识别分类与异常检测间的冲突场景。
- 在内样本中缓解梯度冲突，提升检测性能。
- 适合关注少样本异常检测与模型鲁棒性的研究者。
少样本分布外（OOD）检测旨在仅用少量已知类别图像的情况下，识别未见类别的分布外图像。现有方法将已知类样本的背景区域视为分布外知识，并同时进行分布外正则化与已知类分类优化。然而，由于识别偏差，已知类分类优化与分布外正则化之间仍存在梯度冲突。为此，本文提出梯度对齐上下文优化（GaCoOp），通过分解优化梯度识别冲突发生场景，并在内部已知样本中缓解冲突，同时利用梯度投影优化提示词。在大规模 ImageNet OOD 检测基准上的大量实验表明，所提方法能有效缓解梯度冲突并取得优异性能。代码将发布于 https://github.com/BaoshunWq/ood-GaCoOp。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。