# Controllable Continual Test-Time Adaptation

arXiv: https://arxiv.org/abs/2405.14602 · HTML: https://mlsanity.com/paper/2405.14602/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 60 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [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)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Acquisition of Chess Knowledge in AlphaZero](https://mlsanity.com/paper/2111.09259/) (2021)
- [Robust Mean Teacher for Continual and Gradual Test-Time Adaptation](https://mlsanity.com/paper/2211.13081/) (2022)
- [Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation](https://mlsanity.com/paper/2212.04145/) (2022)
- [ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation](https://mlsanity.com/paper/2306.04344/) (2023)
- [Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement](https://mlsanity.com/paper/2203.08008/) (2022)
- [A Probabilistic Framework for Lifelong Test-Time Adaptation](https://mlsanity.com/paper/2212.09713/) (2022)
- [Exploring Example Influence in Continual Learning](https://mlsanity.com/paper/2209.12241/) (2022)
- [Continual Test-time Domain Adaptation via Dynamic Sample Selection](https://mlsanity.com/paper/2310.03335/) (2023)
- [Each Test Image Deserves A Specific Prompt: Continual Test-Time Adaptation for 2D Medical Image Segmentation](https://mlsanity.com/paper/2311.18363/) (2023)
- [What is Wrong with Continual Learning in Medical Image Segmentation?](https://mlsanity.com/paper/2010.11008/) (2020)
- [Multi-Domain Multi-Task Rehearsal for Lifelong Learning](https://mlsanity.com/paper/2012.07236/) (2020)
- [Sim-to-Real Domain Adaptation for Lane Detection and Classification in Autonomous Driving](https://mlsanity.com/paper/2202.07133/) (2022)
- [From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space](https://mlsanity.com/paper/2308.09437/) (2023)
- [Position: Explain to Question not to Justify](https://mlsanity.com/paper/2402.13914/) (2024)
- [Reveal to Revise: An Explainable AI Life Cycle for Iterative Bias Correction of Deep Models](https://mlsanity.com/paper/2303.12641/) (2023)

## Built on by (most cited first, 6 of 6)

- [Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection](https://mlsanity.com/paper/2409.08566/) (2024)
- [Test-Time Discovery via Hashing Memory](https://mlsanity.com/paper/2503.10699/) (2025)
- [Live Interactive Training for Video Segmentation](https://mlsanity.com/paper/2603.26929/) (2026)
- [Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions](https://mlsanity.com/paper/2607.08164/) (2026)
- [Rethinking the Teacher-Student Framework for Test-Time Adaptation](https://mlsanity.com/paper/2609.02507/) (2026)
- [When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation](https://mlsanity.com/paper/2609.37602/) (2026)

## Abstract (arXiv)

Continual Test-Time Adaptation (CTTA) is an emerging and challenging task where a model trained in a source domain must adapt to continuously changing conditions during testing, without access to the original source data. CTTA is prone to error accumulation due to uncontrollable domain shifts, leading to blurred decision boundaries between categories. Existing CTTA methods primarily focus on suppressing domain shifts, which proves inadequate during the unsupervised test phase. In contrast, we introduce a novel approach that guides rather than suppresses these shifts. Specifically, we propose Controllable Continual Test-Time Adaptation (C-CoTTA), which explicitly prevents any single category from encroaching on others, thereby mitigating the mutual influence between categories caused by uncontrollable shifts. Moreover, our method reduces the sensitivity of model to domain transformations, thereby minimizing the magnitude of category shifts. Extensive quantitative experiments demonstrate the effectiveness of our method, while qualitative analyses, such as t-SNE plots, confirm the theoretical validity of our approach.