# Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/2108.06583 · HTML: https://mlsanity.com/paper/2108.06583/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 31 references that are in the map.
- First posted on arXiv 14 Aug 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [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)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Deep Transfer Learning with Joint Adaptation Networks](https://mlsanity.com/paper/1605.06636/) (2016)
- [VisDA: The Visual Domain Adaptation Challenge](https://mlsanity.com/paper/1710.06924/) (2017)
- [Multi-Adversarial Domain Adaptation](https://mlsanity.com/paper/1809.02176/) (2018)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations](https://mlsanity.com/paper/2003.12237/) (2020)
- [Dual Mixup Regularized Learning for Adversarial Domain Adaptation](https://mlsanity.com/paper/2007.03141/) (2020)
- [Multinomial Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/1802.05694/) (2018)
- [Transfer Learning with Dynamic Adversarial Adaptation Network](https://mlsanity.com/paper/1909.08184/) (2019)
- [Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2007.07695/) (2020)
- [Conditional Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2102.10176/) (2021)
- [Dual Adversarial Co-Learning for Multi-Domain Text Classification](https://mlsanity.com/paper/1909.08203/) (2019)
- [Mixup Regularized Adversarial Networks for Multi-Domain Text Classification](https://mlsanity.com/paper/2102.00467/) (2021)

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

- [Co-Regularized Adversarial Learning for Multi-Domain Text Classification](https://mlsanity.com/paper/2201.12796/) (2022)
- [Maximum Batch Frobenius Norm for Multi-Domain Text Classification](https://mlsanity.com/paper/2202.00537/) (2022)

## Abstract (arXiv)

Adversarial domain adaptation has made impressive advances in transferring knowledge from the source domain to the target domain by aligning feature distributions of both domains. These methods focus on minimizing domain divergence and regard the adaptability, which is measured as the expected error of the ideal joint hypothesis on these two domains, as a small constant. However, these approaches still face two issues: (1) Adversarial domain alignment distorts the original feature distributions, deteriorating the adaptability; (2) Transforming feature representations to be domain-invariant needs to sacrifice domain-specific variations, resulting in weaker discriminability. In order to alleviate these issues, we propose category-invariant feature enhancement (CIFE), a general mechanism that enhances the adversarial domain adaptation through optimizing the adaptability. Specifically, the CIFE approach introduces category-invariant features to boost the discriminability of domain-invariant features with preserving the transferability. Experiments show that the CIFE could improve upon representative adversarial domain adaptation methods to yield state-of-the-art results on five benchmarks.