# ACDC: Online Unsupervised Cross-Domain Adaptation

arXiv: https://arxiv.org/abs/2110.01326 · HTML: https://mlsanity.com/paper/2110.01326/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 50 references that are in the map.
- First posted on arXiv 4 Oct 2021.

## Builds on (most cited first, 11 of 11)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [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)
- [Generate To Adapt: Aligning Domains using Generative Adversarial Networks](https://mlsanity.com/paper/1704.01705/) (2017)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [Scikit-Multiflow: A Multi-output Streaming Framework](https://mlsanity.com/paper/1807.04662/) (2018)
- [Every Model Learned by Gradient Descent Is Approximately a Kernel Machine](https://mlsanity.com/paper/2012.00152/) (2020)
- [Discriminative Feature Alignment: Improving Transferability of Unsupervised Domain Adaptation by Gaussian-guided Latent Alignment](https://mlsanity.com/paper/2006.12770/) (2020)
- [Multi-Source Transfer Learning for Non-Stationary Environments](https://mlsanity.com/paper/1901.02052/) (2019)
- [ATL: Autonomous Knowledge Transfer from Many Streaming Processes](https://mlsanity.com/paper/1910.03434/) (2019)
- [Automatic Online Multi-Source Domain Adaptation](https://mlsanity.com/paper/2109.01996/) (2021)

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

- [Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition](https://mlsanity.com/paper/2401.11085/) (2024)
- [Autonomous Cross Domain Adaptation under Extreme Label Scarcity](https://mlsanity.com/paper/2209.01548/) (2022)
- [Towards Cross-Domain Continual Learning](https://mlsanity.com/paper/2402.12490/) (2024)
- [Cross-Domain Continual Learning via CLAMP](https://mlsanity.com/paper/2405.07142/) (2024)

## Abstract (arXiv)

We consider the problem of online unsupervised cross-domain adaptation, where two independent but related data streams with different feature spaces -- a fully labeled source stream and an unlabeled target stream -- are learned together. Unique characteristics and challenges such as covariate shift, asynchronous concept drifts, and contrasting data throughput arises. We propose ACDC, an adversarial unsupervised domain adaptation framework that handles multiple data streams with a complete self-evolving neural network structure that reacts to these defiances. ACDC encapsulates three modules into a single model: A denoising autoencoder that extracts features, an adversarial module that performs domain conversion, and an estimator that learns the source stream and predicts the target stream. ACDC is a flexible and expandable framework with little hyper-parameter tunability. Our experimental results under the prequential test-then-train protocol indicate an improvement in target accuracy over the baseline methods, achieving more than a 10% increase in some cases.