# Target Domain Data induces Negative Transfer in Mixed Domain Training with Disjoint Classes

arXiv: https://arxiv.org/abs/2303.01003 · HTML: https://mlsanity.com/paper/2303.01003/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 44 references that are in the map.
- First posted on arXiv 2 Mar 2023.

## Builds on (most cited first, 26 of 26)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deeper, Broader and Artier Domain Generalization](https://mlsanity.com/paper/1710.03077/) (2017)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [A systematic study of the class imbalance problem in convolutional neural networks](https://mlsanity.com/paper/1710.05381/) (2017)
- [Self-Challenging Improves Cross-Domain Generalization](https://mlsanity.com/paper/2007.02454/) (2020)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Improve Unsupervised Domain Adaptation with Mixup Training](https://mlsanity.com/paper/2001.00677/) (2020)
- [Efficient parametrization of multi-domain deep neural networks](https://mlsanity.com/paper/1803.10082/) (2018)
- [Partial Adversarial Domain Adaptation](https://mlsanity.com/paper/1808.04205/) (2018)
- [A Survey on Negative Transfer](https://mlsanity.com/paper/2009.00909/) (2020)
- [Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift](https://mlsanity.com/paper/1803.00830/) (2018)
- [Towards Universal Object Detection by Domain Attention](https://mlsanity.com/paper/1904.04402/) (2019)
- [Excessive Invariance Causes Adversarial Vulnerability](https://mlsanity.com/paper/1811.00401/) (2018)
- [Deep Residual Correction Network for Partial Domain Adaptation](https://mlsanity.com/paper/2004.04914/) (2020)
- [Synthetic Examples Improve Generalization for Rare Classes](https://mlsanity.com/paper/1904.05916/) (2019)
- [A Survey on Open Set Recognition](https://mlsanity.com/paper/2109.00893/) (2021)
- [mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets](https://mlsanity.com/paper/2012.08385/) (2020)
- [Road images augmentation with synthetic traffic signs using neural networks](https://mlsanity.com/paper/2101.04927/) (2021)
- [Domain Adaptation for Rare Classes Augmented with Synthetic Samples](https://mlsanity.com/paper/2110.12216/) (2021)
- [Image-to-Image Translation of Synthetic Samples for Rare Classes](https://mlsanity.com/paper/2106.12212/) (2021)

## Abstract (arXiv)

In practical scenarios, it is often the case that the available training data within the target domain only exist for a limited number of classes, with the remaining classes only available within surrogate domains. We show that including the target domain in training when there exist disjoint classes between the target and surrogate domains creates significant negative transfer, and causes performance to significantly decrease compared to training without the target domain at all. We hypothesize that this negative transfer is due to an intermediate shortcut that only occurs when multiple source domains are present, and provide experimental evidence that this may be the case. We show that this phenomena occurs on over 25 distinct domain shifts, both synthetic and real, and in many cases deteriorates the performance to well worse than random, even when using state-of-the-art domain adaptation methods.