Self-Supervised Dynamic Networks for Covariate Shift Robustness

Abstract

As supervised learning still dominates most AI applications, test-time performance is often unexpected. Specifically, a shift of the input covariates, caused by typical nuisances like background-noise, illumination variations or transcription errors, can lead to a significant decrease in prediction accuracy. Recently, it was shown that incorporating self-supervision can significantly improve covariate shift robustness. In this work, we propose Self-Supervised Dynamic Networks (SSDN): an input-dependent mechanism, inspired by dynamic networks, that allows a self-supervised network to predict the weights of the main network, and thus directly handle covariate shifts at test-time. We present the conceptual and empirical advantages of the proposed method on the problem of image classification under different covariate shifts, and show that it significantly outperforms comparable methods.

References in corpus (15)

• A Simple Framework for Contrastive Learning of Visual Representations
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• How transferable are features in deep neural networks?
• Deep Domain Confusion: Maximizing for Domain Invariance
• Deep Visual Domain Adaptation: A Survey
• Unsupervised Data Augmentation for Consistency Training
• Momentum Contrast for Unsupervised Visual Representation Learning
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Do CIFAR-10 Classifiers Generalize to CIFAR-10?
• Domain-Adversarial Training of Neural Networks
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• One-Shot Adaptation of Supervised Deep Convolutional Models
• Deep Verifier Networks: Verification of Deep Discriminative Models with Deep Generative Models
• Hyper-Graph-Network Decoders for Block Codes
• Domain-Aware Dynamic Networks