# TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

arXiv: https://arxiv.org/abs/2303.09870 · HTML: https://mlsanity.com/paper/2303.09870/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Placed in

- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 30 of 37)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Playing for Data: Ground Truth from Computer Games](https://mlsanity.com/paper/1608.02192/) (2016)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks](https://mlsanity.com/paper/1807.07356/) (2018)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift](https://mlsanity.com/paper/2006.10963/) (2020)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learning](https://mlsanity.com/paper/2002.06470/) (2020)
- [Generalized Source-free Domain Adaptation](https://mlsanity.com/paper/2108.01614/) (2021)
- [MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data](https://mlsanity.com/paper/2002.03366/) (2020)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation](https://mlsanity.com/paper/2205.04183/) (2022)
- [Towards Inheritable Models for Open-Set Domain Adaptation](https://mlsanity.com/paper/2004.04388/) (2020)
- [Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentation](https://mlsanity.com/paper/2002.09103/) (2020)

## Built on by (most cited first, 28 of 28)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [Domain Generalization for Medical Image Analysis: A Review](https://mlsanity.com/paper/2310.08598/) (2023)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Frustratingly Easy Test-Time Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18330/) (2024)
- [A Survey on the Robustness of Computer Vision Models against Common Corruptions](https://mlsanity.com/paper/2305.06024/) (2023)
- [T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory](https://mlsanity.com/paper/2403.10052/) (2024)
- [TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight](https://mlsanity.com/paper/2410.15674/) (2024)
- [A Survey on Domain Generalization for Medical Image Analysis](https://mlsanity.com/paper/2402.05035/) (2024)
- [ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains](https://mlsanity.com/paper/2505.14511/) (2025)
- [Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation](https://mlsanity.com/paper/2401.08328/) (2024)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation](https://mlsanity.com/paper/2504.17515/) (2025)
- [From Question to Exploration: Test-Time Adaptation in Semantic Segmentation?](https://mlsanity.com/paper/2310.05341/) (2023)
- [TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models](https://mlsanity.com/paper/2403.11691/) (2024)
- [Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation](https://mlsanity.com/paper/2410.14729/) (2024)
- [Towards Understanding Extrapolation: a Causal Lens](https://mlsanity.com/paper/2501.09163/) (2025)
- [Test-Time Training on Graphs with Large Language Models (LLMs)](https://mlsanity.com/paper/2404.13571/) (2024)
- [Test-Time Augmentation Meets Variational Bayes](https://mlsanity.com/paper/2409.12587/) (2024)
- [DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation](https://mlsanity.com/paper/2506.23104/) (2025)
- [Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation](https://mlsanity.com/paper/2604.10950/) (2026)
- [Improving Entropy-Based Test-Time Adaptation from a Clustering View](https://mlsanity.com/paper/2310.20327/) (2023)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time](https://mlsanity.com/paper/2410.01083/) (2024)
- [When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness](https://mlsanity.com/paper/2606.06938/) (2026)
- [CNG-SFDA:Clean-and-Noisy Region Guided Online-Offline Source-Free Domain Adaptation](https://mlsanity.com/paper/2401.14587/) (2024)
- [Should Bias be Eliminated? A General Framework to Use Bias for OOD Generalization](https://mlsanity.com/paper/2507.17001/) (2025)
- [From Noisy to Native: LLM-driven Graph Restoration for Test-Time Graph Domain Adaptation](https://mlsanity.com/paper/2510.07762/) (2025)
- [Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation](https://mlsanity.com/paper/2606.22351/) (2026)

## Abstract (arXiv)

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Test-time Self-Learning method with automatic Adversarial augmentation dubbed TeSLA for adapting a pre-trained source model to the unlabeled streaming test data. In contrast to conventional self-learning methods based on cross-entropy, we introduce a new test-time loss function through an implicitly tight connection with the mutual information and online knowledge distillation. Furthermore, we propose a learnable efficient adversarial augmentation module that further enhances online knowledge distillation by simulating high entropy augmented images. Our method achieves state-of-the-art classification and segmentation results on several benchmarks and types of domain shifts, particularly on challenging measurement shifts of medical images. TeSLA also benefits from several desirable properties compared to competing methods in terms of calibration, uncertainty metrics, insensitivity to model architectures, and source training strategies, all supported by extensive ablations. Our code and models are available on GitHub.