arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.00192cs.LGcs.AI
收藏

用于分布外检测的层自适应深度神经网络

Layer Adaptive Deep Neural Networks for Out-of-distribution Detection

University of Texas at Dallas(德克萨斯大学达拉斯分校)

Haoliang Wang, Chen Zhao, Xujiang Zhao, Feng Chen

摘要:

在深度神经网络(DNN)的前向传递过程中,输入逐渐从低级特征转换为高级概念标签。虽然不同层的特征可以概括不同层次输入的重要因素,但现代的分布外(OOD)检测方法主要集中在利用其结束层特征。在本文中,我们提出了一种新的层自适应OOD检测框架(LA-OOD)的DNN,可以充分利用中间层的输出。具体来说,我们不是在固定的结束层训练统一的OOD检测器,而是在中间层同时训练多个One-Class SVM OOD检测器,以利用在DNN的不同深度编码的全谱特征。我们开发了一个简单而有效的层自适应的政策,以确定最好的层检测每个潜在的OOD的例子。LA-OOD可以应用于任何现有的DNN,并且在训练期间不需要访问OOD样本。使用三个不同深度和架构的DNN,我们的实验表明,LA-OOD对不同复杂度的OOD具有鲁棒性,并且在一些真实世界的数据集上可以大幅超越最先进的竞争对手。

英文摘要:

During the forward pass of Deep Neural Networks (DNNs), inputs gradually transformed from low-level features to high-level conceptual labels. While features at different layers could summarize the important factors of the inputs at varying levels, modern out-of-distribution (OOD) detection methods mostly focus on utilizing their ending layer features. In this paper, we proposed a novel layer-adaptive OOD detection framework (LA-OOD) for DNNs that can fully utilize the intermediate layers' outputs. Specifically, instead of training a unified OOD detector at a fixed ending layer, we train multiple One-Class SVM OOD detectors simultaneously at the intermediate layers to exploit the full spectrum characteristics encoded at varying depths of DNNs. We develop a simple yet effective layer-adaptive policy to identify the best layer for detecting each potential OOD example. LA-OOD can be applied to any existing DNNs and does not require access to OOD samples during the training. Using three DNNs of varying depth and architectures, our experiments demonstrate that LA-OOD is robust against OODs of varying complexity and can outperform state-of-the-art competitors by a large margin on some real-world datasets.

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。

↑