# Rethinking Precision of Pseudo Label: Test-Time Adaptation via Complementary Learning

arXiv: https://arxiv.org/abs/2301.06013 · HTML: https://mlsanity.com/paper/2301.06013/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 15 Jan 2023.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Suppressing Uncertainties for Large-Scale Facial Expression Recognition](https://mlsanity.com/paper/2002.10392/) (2020)
- [On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness](https://mlsanity.com/paper/2102.11273/) (2021)
- [Learning with Biased Complementary Labels](https://mlsanity.com/paper/1711.09535/) (2017)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [FINE Samples for Learning with Noisy Labels](https://mlsanity.com/paper/2102.11628/) (2021)
- [Sample Selection with Uncertainty of Losses for Learning with Noisy Labels](https://mlsanity.com/paper/2106.00445/) (2021)
- [A Topological Filter for Learning with Label Noise](https://mlsanity.com/paper/2012.04835/) (2020)
- [Error-Bounded Correction of Noisy Labels](https://mlsanity.com/paper/2011.10077/) (2020)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [Complementary-Label Learning for Arbitrary Losses and Models](https://mlsanity.com/paper/1810.04327/) (2018)
- [Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1808.09347/) (2018)
- [If your data distribution shifts, use self-learning](https://mlsanity.com/paper/2104.12928/) (2021)
- [Negative sampling in semi-supervised learning](https://mlsanity.com/paper/1911.05166/) (2019)
- [SceneAdapt: Scene-based domain adaptation for semantic segmentation using adversarial learning](https://mlsanity.com/paper/2006.10386/) (2020)

## Built on by (most cited first, 14 of 14)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical](https://mlsanity.com/paper/2311.15502/) (2023)
- [MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection](https://mlsanity.com/paper/2406.14878/) (2024)
- [DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection](https://mlsanity.com/paper/2406.13891/) (2024)
- [Test-time Correlation Alignment](https://mlsanity.com/paper/2505.00533/) (2025)
- [PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation](https://mlsanity.com/paper/2506.02453/) (2025)
- [Category-wise Fine-Tuning: Resisting Incorrect Pseudo-Labels in Multi-Label Image Classification with Partial Labels](https://mlsanity.com/paper/2401.16991/) (2024)
- [FRET: Feature Redundancy Elimination for Test Time Adaptation](https://mlsanity.com/paper/2505.10641/) (2025)
- [CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving](https://mlsanity.com/paper/2505.16524/) (2025)
- [ESP-Zero: Unsupervised enhancement of zero-shot classification for Extremely Sparse Point cloud](https://mlsanity.com/paper/2404.19639/) (2024)
- [Learning Robustness at Test-Time from a Non-Robust Teacher](https://mlsanity.com/paper/2604.11590/) (2026)
- [Recent advances in weakly supervised learning: New supervision paradigms, assumption relaxations, and practical solutions](https://mlsanity.com/paper/2608.06896/) (2026)
- [Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs](https://mlsanity.com/paper/2608.27948/) (2026)

## Abstract (arXiv)

In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation tasks, information from the source domain is typically unavailable and the model has to be optimized without supervision for test-time samples. Hence, usual methods assign labels for unannotated data with the prediction by a well-trained source model in an unsupervised learning framework. Previous studies have employed unsupervised objectives, such as the entropy of model predictions, as optimization targets to effectively learn features for test-time samples. However, the performance of the model is easily compromised by the quality of pseudo-labels, since inaccuracies in pseudo-labels introduce noise to the model. Therefore, we propose to leverage the "less probable categories" to decrease the risk of incorrect pseudo-labeling. The complementary label is introduced to designate these categories. We highlight that the risk function of complementary labels agrees with their Vanilla loss formula under the conventional true label distribution. Experiments show that the proposed learning algorithm achieves state-of-the-art performance on different datasets and experiment settings.