# Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization

arXiv: https://arxiv.org/abs/1801.10068 · HTML: https://mlsanity.com/paper/1801.10068/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jan 2018.

## Built on by (most cited first, 30 of 40)

- [FSDR: Frequency Space Domain Randomization for Domain Generalization](https://mlsanity.com/paper/2103.02370/) (2021)
- [Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives](https://mlsanity.com/paper/2208.07422/) (2022)
- [ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity](https://mlsanity.com/paper/2203.08101/) (2022)
- [Category Contrast for Unsupervised Domain Adaptation in Visual Tasks](https://mlsanity.com/paper/2106.02885/) (2021)
- [A Prototype-Oriented Framework for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2110.12024/) (2021)
- [CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2107.00085/) (2021)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID](https://mlsanity.com/paper/2108.02413/) (2021)
- [RDA: Robust Domain Adaptation via Fourier Adversarial Attacking](https://mlsanity.com/paper/2106.02874/) (2021)
- [Semantic Concentration for Domain Adaptation](https://mlsanity.com/paper/2108.05720/) (2021)
- [ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2106.10812/) (2021)
- [A Survey of Unsupervised Domain Adaptation for Visual Recognition](https://mlsanity.com/paper/2112.06745/) (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)
- [Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2104.01286/) (2021)
- [Unsupervised Domain Adaptation via Domain-Adaptive Diffusion](https://mlsanity.com/paper/2308.13893/) (2023)
- [Multi-Representation Adaptation Network for Cross-domain Image Classification](https://mlsanity.com/paper/2201.01002/) (2022)
- [MemSAC: Memory Augmented Sample Consistency for Large Scale Unsupervised Domain Adaptation](https://mlsanity.com/paper/2207.12389/) (2022)
- [Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation](https://mlsanity.com/paper/2107.06154/) (2021)
- [Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation](https://mlsanity.com/paper/2203.04156/) (2022)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation](https://mlsanity.com/paper/2204.02111/) (2022)
- [Generalized Universal Domain Adaptation with Generative Flow Networks](https://mlsanity.com/paper/2305.04466/) (2023)
- [CoC-VLA: Delving into Adversarial Domain Transfer for Explainable Autonomous Driving via Chain-of-Causality Visual-Language-Action Model](https://mlsanity.com/paper/2511.19914/) (2025)
- [Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment](https://mlsanity.com/paper/2106.02845/) (2021)
- [Domain Attention Consistency for Multi-Source Domain Adaptation](https://mlsanity.com/paper/2111.03911/) (2021)
- [Exploiting Robust Unsupervised Video Person Re-identification](https://mlsanity.com/paper/2111.05170/) (2021)
- [Mitigating Uncertainty of Classifier for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2107.00727/) (2021)
- [Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains](https://mlsanity.com/paper/2203.01682/) (2022)
- [A Prototype-Oriented Clustering for Domain Shift with Source Privacy](https://mlsanity.com/paper/2302.03807/) (2023)

## Abstract (arXiv)

In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN). First, our approach transfers knowledge in all the convolutional layers through attention alignment. Most previous methods align high-level representations, e.g., activations of the fully connected (FC) layers. In these methods, however, the convolutional layers which underpin critical low-level domain knowledge cannot be updated directly towards reducing domain discrepancy. Specifically, we assume that the discriminative regions in an image are relatively invariant to image style changes. Based on this assumption, we propose an attention alignment scheme on all the target convolutional layers to uncover the knowledge shared by the source domain. Second, we estimate the posterior label distribution of the unlabeled data for target network training. Previous methods, which iteratively update the pseudo labels by the target network and refine the target network by the updated pseudo labels, are vulnerable to label estimation errors. Instead, our approach uses category distribution to calculate the cross-entropy loss for training, thereby ameliorating the error accumulation of the estimated labels. The two contributions allow our approach to outperform the state-of-the-art methods by +2.6% on the Office-31 dataset.