# Continual Domain Adversarial Adaptation via Double-Head Discriminators

arXiv: https://arxiv.org/abs/2402.03588 · HTML: https://mlsanity.com/paper/2402.03588/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 98 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 30 of 46)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [Large Scale Incremental Learning](https://mlsanity.com/paper/1905.13260/) (2019)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [End-to-End Incremental Learning](https://mlsanity.com/paper/1807.09536/) (2018)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Measuring Catastrophic Forgetting in Neural Networks](https://mlsanity.com/paper/1708.02072/) (2017)
- [Bridging Theory and Algorithm for Domain Adaptation](https://mlsanity.com/paper/1904.05801/) (2019)
- [On Tiny Episodic Memories in Continual Learning](https://mlsanity.com/paper/1902.10486/) (2019)
- [Beto, Bentz, Becas: The Surprising Cross-Lingual Effectiveness of BERT](https://mlsanity.com/paper/1904.09077/) (2019)
- [Maintaining Discrimination and Fairness in Class Incremental Learning](https://mlsanity.com/paper/1911.07053/) (2019)
- [Learning without Memorizing](https://mlsanity.com/paper/1811.08051/) (2018)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [REMIND Your Neural Network to Prevent Catastrophic Forgetting](https://mlsanity.com/paper/1910.02509/) (2019)

## Built on by (most cited first, 4 of 4)

- [TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram](https://mlsanity.com/paper/2412.07980/) (2024)
- [Low-Rank Continual Pyramid Vision Transformer: Incrementally Segment Whole-Body Organs in CT with Light-Weighted Adaptation](https://mlsanity.com/paper/2410.04689/) (2024)
- [Finding Structure in Continual Learning](https://mlsanity.com/paper/2602.04555/) (2026)
- [Task Switching Without Forgetting via Proximal Decoupling](https://mlsanity.com/paper/2604.18857/) (2026)

## Abstract (arXiv)

Domain adversarial adaptation in a continual setting poses a significant challenge due to the limitations on accessing previous source domain data. Despite extensive research in continual learning, the task of adversarial adaptation cannot be effectively accomplished using only a small number of stored source domain data, which is a standard setting in memory replay approaches. This limitation arises from the erroneous empirical estimation of gH-divergence with few source domain samples. To tackle this problem, we propose a double-head discriminator algorithm, by introducing an addition source-only domain discriminator that are trained solely on source learning phase. We prove that with the introduction of a pre-trained source-only domain discriminator, the empirical estimation error of gH-divergence related adversarial loss is reduced from the source domain side. Further experiments on existing domain adaptation benchmark show that our proposed algorithm achieves more than 2% improvement on all categories of target domain adaptation task while significantly mitigating the forgetting on source domain.