# Towards Robust Cross-domain Image Understanding with Unsupervised Noise Removal

arXiv: https://arxiv.org/abs/2109.04284 · HTML: https://mlsanity.com/paper/2109.04284/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Learning Transferable Features with Deep Adaptation Networks](https://mlsanity.com/paper/1502.02791/) (2015)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Unsupervised Domain Adaptation with Residual Transfer Networks](https://mlsanity.com/paper/1602.04433/) (2016)
- [Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation](https://mlsanity.com/paper/1809.09478/) (2018)
- [Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2101.10979/) (2021)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning](https://mlsanity.com/paper/1702.08811/) (2017)
- [Progressive Feature Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.08585/) (2018)
- [Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2007.09222/) (2020)
- [Domain Adaptation with Conditional Distribution Matching and Generalized Label Shift](https://mlsanity.com/paper/2003.04475/) (2020)
- [Robust Classification with Convolutional Prototype Learning](https://mlsanity.com/paper/1805.03438/) (2018)
- [Cluster Alignment with a Teacher for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.09980/) (2019)
- [Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis](https://mlsanity.com/paper/2007.07222/) (2020)
- [The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition](https://mlsanity.com/paper/1511.06789/) (2015)
- [COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19](https://mlsanity.com/paper/2005.01577/) (2020)
- [MLCask: Efficient Management of Component Evolution in Collaborative Data Analytics Pipelines](https://mlsanity.com/paper/2010.10246/) (2020)
- [Butterfly: One-step Approach towards Wildly Unsupervised Domain Adaptation](https://mlsanity.com/paper/1905.07720/) (2019)

## Built on by (most cited first, 2 of 2)

- [From Plate to Prevention: A Dietary Nutrient-aided Platform for Health Promotion in Singapore](https://mlsanity.com/paper/2301.03829/) (2023)
- [Cohort-Anchored Foundation Models for Electronic Health Records: From Risk Scores to Auditable Peer Cohorts](https://mlsanity.com/paper/2606.21885/) (2026)

## Abstract (arXiv)

Deep learning models usually require a large amount of labeled data to achieve satisfactory performance. In multimedia analysis, domain adaptation studies the problem of cross-domain knowledge transfer from a label rich source domain to a label scarce target domain, thus potentially alleviates the annotation requirement for deep learning models. However, we find that contemporary domain adaptation methods for cross-domain image understanding perform poorly when source domain is noisy. Weakly Supervised Domain Adaptation (WSDA) studies the domain adaptation problem under the scenario where source data can be noisy. Prior methods on WSDA remove noisy source data and align the marginal distribution across domains without considering the fine-grained semantic structure in the embedding space, which have the problem of class misalignment, e.g., features of cats in the target domain might be mapped near features of dogs in the source domain. In this paper, we propose a novel method, termed Noise Tolerant Domain Adaptation, for WSDA. Specifically, we adopt the cluster assumption and learn cluster discriminatively with class prototypes in the embedding space. We propose to leverage the location information of the data points in the embedding space and model the location information with a Gaussian mixture model to identify noisy source data. We then design a network which incorporates the Gaussian mixture noise model as a sub-module for unsupervised noise removal and propose a novel cluster-level adversarial adaptation method which aligns unlabeled target data with the less noisy class prototypes for mapping the semantic structure across domains. We conduct extensive experiments to evaluate the effectiveness of our method on both general images and medical images from COVID-19 and e-commerce datasets. The results show that our method significantly outperforms state-of-the-art WSDA methods.