密集连接能否有益于离群点检测？基于NAS的探索之旅
Can Dense Connectivity Benefit Outlier Detection? An Odyssey with NAS
AI总结：
提出基于NAS的离群点检测器密集连接搜索范式DCSOD，通过分层搜索空间探索CNN密集连接，并引入演化蒸馏提升评估稳定性，在CIFAR基准上实现SOTA性能。
摘要：
分布外（OOD）检测的最新进展是卷积神经网络（CNNs）在现实世界应用中安全可靠部署的驱动力。然而，现有研究主要通过置信度分数和基于深度生成模型的方法进行OOD检测，未考虑DNN结构的影响，尤其是架构构建中的密集连接。此外，现有离群点检测方法在泛化性能上表现出高方差，缺乏在评估和排序不同离群点检测器时的稳定性和置信度。在本工作中，我们提出了一种新范式——离群点检测器密集连接搜索（DCSOD），利用神经架构搜索（NAS）自动探索CNN架构在近OOD检测任务上的密集连接。我们引入了一个包含通用卷积算子和密集连接的分层搜索空间，允许对具有多样连接模式的CNN架构进行灵活探索。为提高搜索过程中OOD检测评估的质量，我们基于多视图特征学习解释提出了演化蒸馏。演化蒸馏稳定了OOD检测评估的训练，从而提高了搜索质量。我们在OOD检测协议下，在CIFAR基准上全面检验了DCSOD。实验结果表明，DCSOD在广泛使用的架构和先前的NAS基线上取得了显著性能。值得注意的是，DCSOD在CIFAR基准上达到了最先进的（SOTA）性能，AUROC提升了约1.0%。
英文摘要：
Recent advances in Out-of-Distribution (OOD) Detection is the driving force behind safe and reliable deployment of Convolutional Neural Networks (CNNs) in real world applications. However, existing studies focus on OOD detection through confidence score and deep generative model-based methods, without considering the impact of DNN structures, especially dense connectivity in architecture fabrications. In addition, existing outlier detection approaches exhibit high variance in generalization performance, lacking stability and confidence in evaluating and ranking different outlier detectors. In this work, we propose a novel paradigm, Dense Connectivity Search of Outlier Detector (DCSOD), that automatically explore the dense connectivity of CNN architectures on near-OOD detection task using Neural Architecture Search (NAS). We introduce a hierarchical search space containing versatile convolution operators and dense connectivity, allowing a flexible exploration of CNN architectures with diverse connectivity patterns. To improve the quality of evaluation on OOD detection during search, we propose evolving distillation based on our multi-view feature learning explanation. Evolving distillation stabilizes training for OOD detection evaluation, thus improves the quality of search. We thoroughly examine DCSOD on CIFAR benchmarks under OOD detection protocol. Experimental results show that DCSOD achieve remarkable performance over widely used architectures and previous NAS baselines. Notably, DCSOD achieves state-of-the-art (SOTA) performance on CIFAR benchmark, with AUROC improvement of $\sim$1.0%.
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。
