# Noisy Universal Domain Adaptation via Divergence Optimization for Visual Recognition

arXiv: https://arxiv.org/abs/2304.10333 · HTML: https://mlsanity.com/paper/2304.10333/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 52 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [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)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [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)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [Deep Domain Confusion: Maximizing for Domain Invariance](https://mlsanity.com/paper/1412.3474/) (2014)
- [Towards Open Set Deep Networks](https://mlsanity.com/paper/1511.06233/) (2015)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Are we done with ImageNet?](https://mlsanity.com/paper/2006.07159/) (2020)
- [Training Deep Neural Networks on Noisy Labels with Bootstrapping](https://mlsanity.com/paper/1412.6596/) (2014)
- [Dilated Residual Networks](https://mlsanity.com/paper/1705.09914/) (2017)
- [Joint Optimization Framework for Learning with Noisy Labels](https://mlsanity.com/paper/1803.11364/) (2018)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [The ApolloScape Open Dataset for Autonomous Driving and its Application](https://mlsanity.com/paper/1803.06184/) (2018)
- [Universal Domain Adaptation through Self Supervision](https://mlsanity.com/paper/2002.07953/) (2020)
- [Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1607.03516/) (2016)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Domain Adaptation for Semantic Segmentation with Maximum Squares Loss](https://mlsanity.com/paper/1909.13589/) (2019)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [Unsupervised Cross-Domain Image Generation](https://mlsanity.com/paper/1611.02200/) (2016)
- [Adversarial Dropout Regularization](https://mlsanity.com/paper/1711.01575/) (2017)
- [Importance Weighted Adversarial Nets for Partial Domain Adaptation](https://mlsanity.com/paper/1803.09210/) (2018)
- [Learning to Transfer Examples for Partial Domain Adaptation](https://mlsanity.com/paper/1903.12230/) (2019)

## Abstract (arXiv)

To transfer the knowledge learned from a labeled source domain to an unlabeled target domain, many studies have worked on universal domain adaptation (UniDA), where there is no constraint on the label sets of the source domain and target domain. However, the existing UniDA methods rely on source samples with correct annotations. Due to the limited resources in the real world, it is difficult to obtain a large amount of perfectly clean labeled data in a source domain in some applications. As a result, we propose a novel realistic scenario named Noisy UniDA, in which classifiers are trained using noisy labeled data from the source domain as well as unlabeled domain data from the target domain that has an uncertain class distribution. A multi-head convolutional neural network framework is proposed in this paper to address all of the challenges faced in the Noisy UniDA at once. Our network comprises a single common feature generator and multiple classifiers with various decision bounds. We can detect noisy samples in the source domain, identify unknown classes in the target domain, and align the distribution of the source and target domains by optimizing the divergence between the outputs of the various classifiers. The proposed method outperformed the existing methods in most of the settings after a thorough analysis of the various domain adaption scenarios. The source code is available at urlhttps://github.com/YU1ut/Divergence-Optimization.