# Conditional Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/1705.10667 · HTML: https://mlsanity.com/paper/1705.10667/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2017.

## Built on by (most cited first, 10 of 10)

- [SeMAnD: Self-Supervised Anomaly Detection in Multimodal Geospatial Datasets](https://mlsanity.com/paper/2309.15245/) (2023)
- [Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation](https://mlsanity.com/paper/2402.04929/) (2024)
- [GaitSADA: Self-Aligned Domain Adaptation for mmWave Gait Recognition](https://mlsanity.com/paper/2301.13384/) (2023)
- [Self-Paced Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2303.05933/) (2023)
- [SADA: Semantic adversarial unsupervised domain adaptation for Temporal Action Localization](https://mlsanity.com/paper/2312.13377/) (2023)
- [Transcending Domains through Text-to-Image Diffusion: A Source-Free Approach to Domain Adaptation](https://mlsanity.com/paper/2310.01701/) (2023)
- [Adversarial Reweighting with α-Power Maximization for Domain Adaptation](https://mlsanity.com/paper/2404.17275/) (2024)
- [MSSDA: Multi-Sub-Source Adaptation for Diabetic Foot Neuropathy Recognition](https://mlsanity.com/paper/2409.14154/) (2024)
- [Unveiling the Superior Paradigm: A Comparative Study of Source-Free Domain Adaptation and Unsupervised Domain Adaptation](https://mlsanity.com/paper/2411.15844/) (2024)
- [Prototypical Distillation and Debiased Tuning for Black-box Unsupervised Domain Adaptation](https://mlsanity.com/paper/2412.20670/) (2024)

## Abstract (arXiv)

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal distributions native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. With theoretical guarantees and a few lines of codes, the approach has exceeded state-of-the-art results on five datasets.