arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.02578cs.CV
收藏

深度单类分类表示的学习与评价

Learning and Evaluating Representations for Deep One-class Classification

Google Cloud AI(谷歌云人工智能)

Kihyuk Sohn, Chun-Liang Li, Jinsung Yoon, Minho Jin, Tomas Pfister

摘要:

我们提出了一个两阶段的框架,深一类分类。我们首先从一类数据中学习自监督表示,然后在学习的表示上构建一类分类器。该框架不仅允许学习更好的表示,而且还允许构建忠实于目标任务的单类分类器。我们认为,在生成或判别模型的统计角度启发的分类器比现有的方法,如从一个代理分类器的正态性得分更有效。我们彻底评估了不同的自我监督表示学习算法下提出的框架一类分类。此外,我们提出了一种新的分布增强的对比学习,通过数据增强来扩展训练分布,以阻碍对比表示的一致性。在实验中,我们展示了视觉域一类分类基准的最先进的性能,包括新颖性和异常检测。最后,我们给出了视觉解释,证实了深度单类分类器的决策过程对人类来说是直观的。该代码可在https://github.com/google-research/deep_representation_one_class上获得。

英文摘要:

We present a two-stage framework for deep one-class classification. We first learn self-supervised representations from one-class data, and then build one-class classifiers on learned representations. The framework not only allows to learn better representations, but also permits building one-class classifiers that are faithful to the target task. We argue that classifiers inspired by the statistical perspective in generative or discriminative models are more effective than existing approaches, such as a normality score from a surrogate classifier. We thoroughly evaluate different self-supervised representation learning algorithms under the proposed framework for one-class classification. Moreover, we present a novel distribution-augmented contrastive learning that extends training distributions via data augmentation to obstruct the uniformity of contrastive representations. In experiments, we demonstrate state-of-the-art performance on visual domain one-class classification benchmarks, including novelty and anomaly detection. Finally, we present visual explanations, confirming that the decision-making process of deep one-class classifiers is intuitive to humans. The code is available at https://github.com/google-research/deep_representation_one_class.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑