Robustness via Cross-Domain Ensembles

Abstract

We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is that predictions made via different cues respond differently to a distribution shift, hence one should be able to merge them into one robust final prediction. We perform the merging in a straightforward but principled manner based on the uncertainty associated with each prediction. The evaluations are performed using multiple tasks and datasets (Taskonomy, Replica, ImageNet, CIFAR) under a wide range of adversarial and non-adversarial distribution shifts which demonstrate the proposed method is considerably more robust than its standard learning counterpart, conventional deep ensembles, and several other baselines.

arXiv commentProject website at https://crossdomain-ensembles.epfl.ch/

References in corpus (23)

• mixup: Beyond Empirical Risk Minimization
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• On Calibration of Modern Neural Networks
• On the Convergence of Adam and Beyond
• Weight Uncertainty in Neural Networks
• Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
• Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
• Deep Anomaly Detection with Outlier Exposure
• The Replica Dataset: A Digital Replica of Indoor Spaces
• Accurate Uncertainties for Deep Learning Using Calibrated Regression
• Multiplicative Normalizing Flows for Variational Bayesian Neural Networks
• Measuring the tendency of CNNs to Learn Surface Statistical Regularities
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batches
• Adversarial Examples Are a Natural Consequence of Test Error in Noise
• Improving Adversarial Robustness of Ensembles with Diversity Training
• BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning
• Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors
• Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
• Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning
• DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
• Noise Contrastive Priors for Functional Uncertainty
• Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus