# Towards Accurate and Robust Domain Adaptation under Noisy Environments

arXiv: https://arxiv.org/abs/2004.12529 · HTML: https://mlsanity.com/paper/2004.12529/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2020.

## Built on by (most cited first, 12 of 12)

- [Towards Robust Adaptive Object Detection under Noisy Annotations](https://mlsanity.com/paper/2204.02620/) (2022)
- [Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation](https://mlsanity.com/paper/2203.04156/) (2022)
- [Enhancing Domain Adaptation through Prompt Gradient Alignment](https://mlsanity.com/paper/2406.09353/) (2024)
- [Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning](https://mlsanity.com/paper/2305.18158/) (2023)
- [Zero-Shot Temporal Resolution Domain Adaptation for Spiking Neural Networks](https://mlsanity.com/paper/2411.04760/) (2024)
- [Towards Corruption-Agnostic Robust Domain Adaptation](https://mlsanity.com/paper/2104.10376/) (2021)
- [GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation](https://mlsanity.com/paper/2201.06001/) (2022)
- [Confusing Pair Correction Based on Category Prototype for Domain Adaptation under Noisy Environments](https://mlsanity.com/paper/2403.12883/) (2024)
- [A Comprehensive Review of Machine Learning Advances on Data Change: A Cross-Field Perspective](https://mlsanity.com/paper/2402.12627/) (2024)
- [Ivan-ISTD: Rethinking Cross-domain Heteroscedastic Noise Perturbations in Infrared Small Target Detection](https://mlsanity.com/paper/2510.12241/) (2025)
- [Dual-Correction Adaptation Network for Noisy Knowledge Transfer](https://mlsanity.com/paper/2207.04423/) (2022)
- [Impact of domain adaptation in deep learning for medical image classifications](https://mlsanity.com/paper/2602.09355/) (2026)

## Abstract (arXiv)

In non-stationary environments, learning machines usually confront the domain adaptation scenario where the data distribution does change over time. Previous domain adaptation works have achieved great success in theory and practice. However, they always lose robustness in noisy environments where the labels and features of examples from the source domain become corrupted. In this paper, we report our attempt towards achieving accurate noise-robust domain adaptation. We first give a theoretical analysis that reveals how harmful noises influence unsupervised domain adaptation. To eliminate the effect of label noise, we propose an offline curriculum learning for minimizing a newly-defined empirical source risk. To reduce the impact of feature noise, we propose a proxy distribution based margin discrepancy. We seamlessly transform our methods into an adversarial network that performs efficient joint optimization for them, successfully mitigating the negative influence from both data corruption and distribution shift. A series of empirical studies show that our algorithm remarkably outperforms state of the art, over 10% accuracy improvements in some domain adaptation tasks under noisy environments.