# AutoDIAL: Automatic DomaIn Alignment Layers

arXiv: https://arxiv.org/abs/1704.08082 · HTML: https://mlsanity.com/paper/1704.08082/

## Key facts

- Cited by 75 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2017.

## Built on by (most cited first, 30 of 75)

- [The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization](https://mlsanity.com/paper/2112.00463/) (2021)
- [Maximizing Confidence Alone Improves Reasoning](https://mlsanity.com/paper/2505.22660/) (2025)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.05988/) (2021)
- [Test-Time Adaptation to Distribution Shift by Confidence Maximization and Input Transformation](https://mlsanity.com/paper/2106.14999/) (2021)
- [Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation](https://mlsanity.com/paper/2108.02376/) (2021)
- [ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2108.06682/) (2021)
- [Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Types](https://mlsanity.com/paper/2103.13318/) (2021)
- [An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions](https://mlsanity.com/paper/2204.08817/) (2022)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [DINE: Domain Adaptation from Single and Multiple Black-box Predictors](https://mlsanity.com/paper/2104.01539/) (2021)
- [Rethinking "Batch" in BatchNorm](https://mlsanity.com/paper/2105.07576/) (2021)
- [Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection](https://mlsanity.com/paper/2110.01428/) (2021)
- [In Search of Lost Online Test-time Adaptation: A Survey](https://mlsanity.com/paper/2310.20199/) (2023)
- [FedDrive: Generalizing Federated Learning to Semantic Segmentation in Autonomous Driving](https://mlsanity.com/paper/2202.13670/) (2022)
- [Compound Domain Generalization via Meta-Knowledge Encoding](https://mlsanity.com/paper/2203.13006/) (2022)
- [Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation](https://mlsanity.com/paper/2106.12497/) (2021)
- [Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation](https://mlsanity.com/paper/2104.00808/) (2021)
- [ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2104.09136/) (2021)
- [Dynamic Transfer for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2103.10583/) (2021)
- [A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologies](https://mlsanity.com/paper/2208.14197/) (2022)
- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://mlsanity.com/paper/2212.00244/) (2022)
- [Domain Adaptation on Point Clouds via Geometry-Aware Implicits](https://mlsanity.com/paper/2112.09343/) (2021)
- [Generalized Domain Conditioned Adaptation Network](https://mlsanity.com/paper/2103.12339/) (2021)
- [DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.09988/) (2022)
- [Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach](https://mlsanity.com/paper/2408.07511/) (2024)
- [Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training](https://mlsanity.com/paper/2204.11590/) (2022)
- [Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation](https://mlsanity.com/paper/2302.02561/) (2023)
- [Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition](https://mlsanity.com/paper/2203.14222/) (2022)
- [Revisiting adapters with adversarial training](https://mlsanity.com/paper/2210.04886/) (2022)

## Abstract (arXiv)

Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attempts to align them have traditionally resulted in works reducing the domain shift by introducing appropriate loss terms, measuring the discrepancies between source and target distributions, in the objective function. Here we take a different route, proposing to align the learned representations by embedding in any given network specific Domain Alignment Layers, designed to match the source and target feature distributions to a reference one. Opposite to previous works which define a priori in which layers adaptation should be performed, our method is able to automatically learn the degree of feature alignment required at different levels of the deep network. Thorough experiments on different public benchmarks, in the unsupervised setting, confirm the power of our approach.