深层验证者网络:深层判别模型与深层生成模型的验证(multimedia)

人工智能安全是许多深度学习应用程序(如自动驾驶)的主要关注点。在一个经过训练的深度学习模型中,一个重要的自然问题是如何可靠地验证模型的预测。在本文中,我们提出了一个新的框架-深度验证网络(DVN)来检测不可靠的输入或预测的深度判别模型,使用单独训练的深度生成模型。该模型基于带解纠缠约束的条件变分自动编码器,将标签信息从潜在表象中分离出来。我们对该模型给出了直观和理论上的证明。利用预测模型对验证者网络进行独立训练,消除了对验证者网络重新训练的需要。我们测试了验证器网络工作,包括非分布检测和反例检测问题,以及结构化的预处理任务中的异常检测问题,如图像字幕生成。我们在所有这些问题上取得了最先进的成果。

原文题目:Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models

原文:AI Safety is a major concern in many deep learn- ing applications such as autonomous driving. Given a trained deep learning model, an important natural problem is how to reliably verify the model’s prediction. In this paper, we propose a novel framework — deep verifier networks (DVN) to detect unreliable inputs or predictions of deep discriminative models, using separately trained deep generative models. Our proposed model is based on conditional variational auto-encoders with disentanglement constraints to separate the label information from the latent representation. We give both intuitive and theoretical justifications for the model. Our verifier network is trained independently with the prediction model, which eliminates the need of retraining the verifier net- work for a new model. We test the verifier net- work on both out-of-distribution detection and adversarial example detection problems, as well as anomaly detection problems in structured pre- diction tasks such as image caption generation. We achieve state-of-the-art results in all of these problems.

原文作者:Tong Che, Xiaofeng Liu, Site Li, Yubin Ge, Ruixiang Zhang, Caiming Xiong, Yoshua Bengio

原文链接:https://arxiv.org/abs/1911.07421