Few-shot OOD detection focuses on recognizing out-of-distribution (OOD)
images that belong to classes unseen during training, with the use of only a
small number of labeled in-distribution (ID) images. Up to now, a mainstream
strategy is based on large-scale vision-language models, such as CLIP. However,
these methods overlook a crucial issue: the lack of reliable OOD supervision
information, which can lead to biased boundaries between in-distribution (ID)
and OOD. To tackle this problem, we propose CLIP-driven Outliers
Synthesis~(CLIP-OS). Firstly, CLIP-OS enhances patch-level features' perception
by newly proposed patch uniform convolution, and adaptively obtains the
proportion of ID-relevant information by employing CLIP-surgery-discrepancy,
thus achieving separation between ID-relevant and ID-irrelevant. Next, CLIP-OS
synthesizes reliable OOD data by mixing up ID-relevant features from different
classes to provide OOD supervision information. Afterward, CLIP-OS leverages
synthetic OOD samples by unknown-aware prompt learning to enhance the
separability of ID and OOD. Extensive experiments across multiple benchmarks
demonstrate that CLIP-OS achieves superior few-shot OOD detection capability.

通过使用 CLIP-OS 方法，在少样本学习中的 OOD 检测中，提出了一种新颖的 patch 均匀卷积和适应性的 ID 相关信息提取方法，并结合合成的可靠 OOD 数据和未知感知的提示学习，实现了 ID 和 OOD 之间的有效区分，从而获得了卓越的性能。

基于 CLIP 的少样本异常检测中的异常合成

CLIP-driven Outliers Synthesis for few-shot OOD detection

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 \textbf{Lo}cal regularized \textbf{Co}ntext
\textbf{Op}timization (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.

我们介绍了一种名为 LoCoOp 的新方法，它针对 few-shot OOD 检测进行本地正则化的上下文优化，利用 CLIP 本地特征的部分作为 OOD 特征，并展示了它在大规模 ImageNet OOD 检测基准测试中的优越性。

LoCoOp: 基于 Prompt 学习的少样本场外检测

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

We ask the following question: what training information is required to
design an effective outlier/out-of-distribution (OOD) detector, i.e., detecting
samples that lie far away from the training distribution? Since unlabeled data
is easily accessible for many applications, the most compelling approach is to
develop detectors based on only unlabeled in-distribution data. However, we
observe that most existing detectors based on unlabeled data perform poorly,
often equivalent to a random prediction. In contrast, existing state-of-the-art
OOD detectors achieve impressive performance but require access to fine-grained
data labels for supervised training. We propose SSD, an outlier detector based
on only unlabeled in-distribution data. We use self-supervised representation
learning followed by a Mahalanobis distance based detection in the feature
space. We demonstrate that SSD outperforms most existing detectors based on
unlabeled data by a large margin. Additionally, SSD even achieves performance
on par, and sometimes even better, with supervised training based detectors.
Finally, we expand our detection framework with two key extensions. First, we
formulate few-shot OOD detection, in which the detector has access to only one
to five samples from each class of the targeted OOD dataset. Second, we extend
our framework to incorporate training data labels, if available. We find that
our novel detection framework based on SSD displays enhanced performance with
these extensions, and achieves state-of-the-art performance. Our code is
publicly available at this https URL

提出了一种仅基于未标记数据进行自监督表征学习的离群检测器 (SSD)，其使用 Mahalanobis 距离在特征空间中进行检测，并通过 few-shot OOD 检测和有监督训练等两个扩展实现了进一步的改进及最先进性能。