Test time Adaptation through Perturbation Robustness
arXiv:2110.10232
Abstract
Data samples generated by several real world processes are dynamic in nature \textit{i.e.}, their characteristics vary with time. Thus it is not possible to train and tackle all possible distributional shifts between training and inference, using the host of transfer learning methods in literature. In this paper, we tackle this problem of adapting to domain shift at inference time \textit{i.e.}, we do not change the training process, but quickly adapt the model at test-time to handle any domain shift. For this, we propose to enforce consistency of predictions of data sampled in the vicinity of test sample on the image manifold. On a host of test scenarios like dealing with corruptions (CIFAR-10-C and CIFAR-100-C), and domain adaptation (VisDA-C), our method is at par or significantly outperforms previous methods.
arXiv commentUnder review
References in corpus (13)
- A Simple Framework for Contrastive Learning of Visual Representations
- Wide Residual Networks
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
- Barlow Twins: Self-Supervised Learning via Redundancy Reduction
- Semi-Supervised Learning with Ladder Networks
- On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
- Model Adaptation: Unsupervised Domain Adaptation without Source Data
- Learning with Pseudo-Ensembles
- Tent: Fully Test-time Adaptation by Entropy Minimization
- Measuring the tendency of CNNs to Learn Surface Statistical Regularities
- RobustBench: a standardized adversarial robustness benchmark
- Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift