Modern deep generative models can assign high likelihood to inputs drawn from outside the training distribution, posing threats to models in open-world deployments. While much research attention has been placed on defining new test-time measures of OOD uncertainty, these methods do not fundamentally change how deep generative models are regularized and optimized in training. In particular, generative models are shown to overly rely on the background information to estimate the likelihood. To address the issue, we propose a novel frequency-regularized learning FRL framework for OOD detection, which incorporates high-frequency information into training and guides the model to focus on semantically relevant features. FRL effectively improves performance on a wide range of generative architectures, including variational auto-encoder, GLOW, and PixelCNN++. On a new large-scale evaluation task, FRL achieves the state-of-the-art performance, outperforming a strong baseline Likelihood Regret by 10.7% (AUROC) while achieving 147$\times$ faster inference speed. Extensive ablations show that FRL improves the OOD detection performance while preserving the image generation quality. Code is available at https://github.com/mu-cai/FRL.
翻译:现代深层基因模型可能极有可能利用从培训分布之外获得的投入,对开放世界部署中的模型构成威胁。虽然许多研究注意力都放在确定新的测试时间测量OOD不确定性的新测试时间测量上,但这些方法并没有从根本上改变深层基因模型在培训中是如何正规化和优化的。特别是,基因模型显示过分依赖背景资料来估计可能性。为了解决这个问题,我们提议建立一个新的频率正规化学习的OOOD FRL检测框架,将高频信息纳入培训,并指导模型侧重于语义相关特征。FRL有效地改进了范围广泛的基因结构的性能,包括变异自动编码器、GLOW和PixelCNN+++。在新的大规模评估任务中,FRL实现了最先进的性能,比强的基线“类似”调高10.7%(AUROC),同时更快地达到147美元/穆的时间值。广泛的浮标显示,FRL改进OOD/FRS的检测性能,同时保持图像的生成质量。 http/AGI/FRCRCR。