Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models

AI Safety is a major concern in many deep learning 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 verify the inputs and outputs of deep discriminative models with deep generative models. Our proposed model is based on conditional variational auto-encoders with disentanglement constraints. We give both intuitive and theoretical justifications of the model. Our verifier network is trained independently with the prediction model, which eliminates the need of retraining the verifier network for a new model. We test the verifier network on out-of-distribution detection and adversarial example detection problems, as well as anomaly detection problems in structured prediction tasks such as image caption generation. We achieve state-of-the-art results in all of these problems.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Alex Krizhevsky,et al.  Learning Multiple Layers of Features from Tiny Images , 2009 .

[3]  Andrew Y. Ng,et al.  Reading Digits in Natural Images with Unsupervised Feature Learning , 2011 .

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Thomas B. Moeslund,et al.  Long-Term Occupancy Analysis Using Graph-Based Optimisation in Thermal Imagery , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[7]  David A. Clifton,et al.  A review of novelty detection , 2014, Signal Process..

[8]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[9]  Yoshua Bengio,et al.  Show, Attend and Tell: Neural Image Caption Generation with Visual Attention , 2015, ICML.

[10]  Yinda Zhang,et al.  LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop , 2015, ArXiv.

[11]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[12]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[13]  Nikos Komodakis,et al.  Wide Residual Networks , 2016, BMVC.

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Ruslan Salakhutdinov,et al.  Importance Weighted Autoencoders , 2015, ICLR.

[16]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[17]  Seyed-Mohsen Moosavi-Dezfooli,et al.  DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[19]  Bernt Schiele,et al.  Learning Deep Representations of Fine-Grained Visual Descriptions , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[21]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[22]  John Schulman,et al.  Concrete Problems in AI Safety , 2016, ArXiv.

[23]  Jane You,et al.  Adaptive Deep Metric Learning for Identity-Aware Facial Expression Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[24]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[25]  Ryan R. Curtin,et al.  Detecting Adversarial Samples from Artifacts , 2017, ArXiv.

[26]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Kevin Gimpel,et al.  A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks , 2016, ICLR.

[28]  David Wagner,et al.  Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods , 2017, AISec@CCS.

[29]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[30]  Kilian Q. Weinberger,et al.  On Calibration of Modern Neural Networks , 2017, ICML.

[31]  Ping Jia,et al.  Line-scan system for continuous hand authentication , 2017 .

[32]  Chao Yang,et al.  Dependency-Aware Attention Control for Unconstrained Face Recognition with Image Sets , 2018, ECCV.

[33]  Prafulla Dhariwal,et al.  Glow: Generative Flow with Invertible 1x1 Convolutions , 2018, NeurIPS.

[34]  Kibok Lee,et al.  Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples , 2017, ICLR.

[35]  Chao Yang,et al.  Ordinal Regression with Neuron Stick-Breaking for Medical Diagnosis , 2018, ECCV Workshops.

[36]  Graham W. Taylor,et al.  Learning Confidence for Out-of-Distribution Detection in Neural Networks , 2018, ArXiv.

[37]  Alexander A. Alemi,et al.  WAIC, but Why? Generative Ensembles for Robust Anomaly Detection , 2018 .

[38]  Yang Zou,et al.  Data Augmentation via Latent Space Interpolation for Image Classification , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[39]  Yang Song,et al.  Constructing Unrestricted Adversarial Examples with Generative Models , 2018, NeurIPS.

[40]  R. Srikant,et al.  Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks , 2017, ICLR.

[41]  Igor M. Quintanilha,et al.  Detecting Out-Of-Distribution Samples Using Low-Order Deep Features Statistics , 2018 .

[42]  James Bailey,et al.  Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality , 2018, ICLR.

[43]  Chao Yang,et al.  Normalized face image generation with perceptron generative adversarial networks , 2018, 2018 IEEE 4th International Conference on Identity, Security, and Behavior Analysis (ISBA).

[44]  Chao Yang,et al.  A joint optimization framework of low-dimensional projection and collaborative representation for discriminative classification , 2018, 2018 24th International Conference on Pattern Recognition (ICPR).

[45]  Kibok Lee,et al.  A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks , 2018, NeurIPS.

[46]  Mingyan Liu,et al.  Spatially Transformed Adversarial Examples , 2018, ICLR.

[47]  Xia Zhu,et al.  Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers , 2018, ECCV.

[48]  Sebastian Nowozin,et al.  Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift , 2019, NeurIPS.

[49]  Yee Whye Teh,et al.  Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality , 2019, ArXiv.

[50]  Yee Whye Teh,et al.  Do Deep Generative Models Know What They Don't Know? , 2018, ICLR.

[51]  Thomas G. Dietterich,et al.  Deep Anomaly Detection with Outlier Exposure , 2018, ICLR.

[52]  Jane You,et al.  Hard negative generation for identity-disentangled facial expression recognition , 2019, Pattern Recognit..

[53]  Jane You,et al.  Feature-Level Frankenstein: Eliminating Variations for Discriminative Recognition , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[54]  Conservative Wasserstein Training for Pose Estimation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[55]  Xiaofeng Liu,et al.  Unimodal-Uniform Constrained Wasserstein Training for Medical Diagnosis , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[56]  Soumya Ghosh,et al.  Quality of Uncertainty Quantification for Bayesian Neural Network Inference , 2019, ArXiv.

[57]  Yoshua Bengio,et al.  Learning deep representations by mutual information estimation and maximization , 2018, ICLR.

[58]  Xiaofeng Liu,et al.  Image2Audio: Facilitating Semi-supervised Audio Emotion Recognition with Facial Expression Image , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[59]  Xiaofeng Liu,et al.  Severity-Aware Semantic Segmentation With Reinforced Wasserstein Training , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[60]  C.-C. Jay Kuo,et al.  Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology , 2021, BrainLes@MICCAI.

[61]  Xiaofeng Liu,et al.  Unimodal regularized neuron stick-breaking for ordinal classification , 2020, Neurocomputing.

[62]  Xiaofeng Liu,et al.  Classification-aware Semi-supervised Domain Adaptation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[63]  Xiaofeng Liu.  Disentanglement for Discriminative Visual Recognition , 2020, ArXiv.

[64]  Tong Che,et al.  AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation , 2020, ECCV.

[65]  Xiaofeng Liu,et al.  Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training , 2020, AAAI.

[66]  Xiaofeng Liu,et al.  Wasserstein Loss based Deep Object Detection , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[67]  Lin Zheng,et al.  Automated interpretation of congenital heart disease from multi-view echocardiograms , 2020, Medical Image Anal..

[68]  Xiaofeng Liu,et al.  Wasserstein Loss With Alternative Reinforcement Learning for Severity-Aware Semantic Segmentation , 2022, IEEE Transactions on Intelligent Transportation Systems.