# Evaluating Continual Test-Time Adaptation for Contextual and Semantic Domain Shifts

arXiv: https://arxiv.org/abs/2208.08767 · HTML: https://mlsanity.com/paper/2208.08767/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 19 references that are in the map.
- First posted on arXiv 18 Aug 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Improving robustness against common corruptions by covariate shift adaptation](https://mlsanity.com/paper/2006.16971/) (2020)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [CORe50: a New Dataset and Benchmark for Continuous Object Recognition](https://mlsanity.com/paper/1705.03550/) (2017)
- [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)
- [A survey on domain adaptation theory: learning bounds and theoretical guarantees](https://mlsanity.com/paper/2004.11829/) (2020)
- [SITA: Single Image Test-time Adaptation](https://mlsanity.com/paper/2112.02355/) (2021)
- [Test-time Batch Statistics Calibration for Covariate Shift](https://mlsanity.com/paper/2110.04065/) (2021)
- [Learning Instance-Specific Adaptation for Cross-Domain Segmentation](https://mlsanity.com/paper/2203.16530/) (2022)

## Built on by (most cited first, 5 of 5)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularization](https://mlsanity.com/paper/2303.01904/) (2023)
- [Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization](https://mlsanity.com/paper/2308.06879/) (2023)
- [Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management](https://mlsanity.com/paper/2212.08356/) (2022)
- [Are Labels Needed for Incremental Instance Learning?](https://mlsanity.com/paper/2301.11417/) (2023)

## Abstract (arXiv)

In this paper, our goal is to adapt a pre-trained convolutional neural network to domain shifts at test time. We do so continually with the incoming stream of test batches, without labels. The existing literature mostly operates on artificial shifts obtained via adversarial perturbations of a test image. Motivated by this, we evaluate the state of the art on two realistic and challenging sources of domain shifts, namely contextual and semantic shifts. Contextual shifts correspond to the environment types, for example, a model pre-trained on indoor context has to adapt to the outdoor context on CORe-50. Semantic shifts correspond to the capture types, for example a model pre-trained on natural images has to adapt to cliparts, sketches, and paintings on DomainNet. We include in our analysis recent techniques such as Prediction-Time Batch Normalization (BN), Test Entropy Minimization (TENT) and Continual Test-Time Adaptation (CoTTA). Our findings are three-fold: i) Test-time adaptation methods perform better and forget less on contextual shifts compared to semantic shifts, ii) TENT outperforms other methods on short-term adaptation, whereas CoTTA outpeforms other methods on long-term adaptation, iii) BN is most reliable and robust. Our code is available at https://github.com/tommiekerssies/Evaluating-Continual-Test-Time-Adaptation-for-Contextual-and-Semantic-Domain-Shifts.