# S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation

arXiv: https://arxiv.org/abs/2109.08901 · HTML: https://mlsanity.com/paper/2109.08901/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 18 Sep 2021.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Deep Hashing Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1706.07522/) (2017)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds](https://mlsanity.com/paper/1906.03671/) (2019)
- [Learning to Adapt Structured Output Space for Semantic Segmentation](https://mlsanity.com/paper/1802.10349/) (2018)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [Variational Adversarial Active Learning](https://mlsanity.com/paper/1904.00370/) (2019)
- [Universal Source-Free Domain Adaptation](https://mlsanity.com/paper/2004.04393/) (2020)
- [A DIRT-T Approach to Unsupervised Domain Adaptation](https://mlsanity.com/paper/1802.08735/) (2018)
- [Adversarial Active Learning for Deep Networks: a Margin Based Approach](https://mlsanity.com/paper/1802.09841/) (2018)
- [Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation](https://mlsanity.com/paper/2007.09222/) (2020)
- [Cross-domain Detection via Graph-induced Prototype Alignment](https://mlsanity.com/paper/2003.12849/) (2020)
- [Adversarial Dropout Regularization](https://mlsanity.com/paper/1711.01575/) (2017)
- [Cluster Alignment with a Teacher for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.09980/) (2019)
- [Active Adversarial Domain Adaptation](https://mlsanity.com/paper/1904.07848/) (2019)
- [Active Domain Adaptation via Clustering Uncertainty-weighted Embeddings](https://mlsanity.com/paper/2010.08666/) (2020)
- [Adversarial-Learned Loss for Domain Adaptation](https://mlsanity.com/paper/2001.01046/) (2020)
- [Towards Inheritable Models for Open-Set Domain Adaptation](https://mlsanity.com/paper/2004.04388/) (2020)
- [Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptation](https://mlsanity.com/paper/2004.04398/) (2020)
- [Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1910.05562/) (2019)
- [Submodular Batch Selection for Training Deep Neural Networks](https://mlsanity.com/paper/1906.08771/) (2019)

## Built on by (most cited first, 19 of 19)

- [A Closer Look at Smoothness in Domain Adversarial Training](https://mlsanity.com/paper/2206.08213/) (2022)
- [Balancing Discriminability and Transferability for Source-Free Domain Adaptation](https://mlsanity.com/paper/2206.08009/) (2022)
- [Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2111.12940/) (2021)
- [A comprehensive survey on deep active learning in medical image analysis](https://mlsanity.com/paper/2310.14230/) (2023)
- [Learning Distinctive Margin toward Active Domain Adaptation](https://mlsanity.com/paper/2203.05738/) (2022)
- [Combating Label Distribution Shift for Active Domain Adaptation](https://mlsanity.com/paper/2208.06604/) (2022)
- [Contributing Dimension Structure of Deep Feature for Coreset Selection](https://mlsanity.com/paper/2401.16193/) (2024)
- [Local Context-Aware Active Domain Adaptation](https://mlsanity.com/paper/2208.12856/) (2022)
- [Spectral Transfer Guided Active Domain Adaptation For Thermal Imagery](https://mlsanity.com/paper/2304.07031/) (2023)
- [Certainty and Uncertainty Guided Active Domain Adaptation](https://mlsanity.com/paper/2505.19421/) (2025)
- [Domain Adversarial Active Learning for Domain Generalization Classification](https://mlsanity.com/paper/2403.06174/) (2024)
- [Loss-based Sequential Learning for Active Domain Adaptation](https://mlsanity.com/paper/2204.11665/) (2022)
- [Scalable Distributed Algorithms for Size-Constrained Submodular Maximization in the MapReduce and Adaptive Complexity Models](https://mlsanity.com/paper/2206.09563/) (2022)
- [D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignment](https://mlsanity.com/paper/2401.05465/) (2024)
- [Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift](https://mlsanity.com/paper/2210.06749/) (2022)
- [Score-Based Methods for Discrete Optimization in Deep Learning](https://mlsanity.com/paper/2310.09890/) (2023)
- [A3: Active Adversarial Alignment for Source-Free Domain Adaptation](https://mlsanity.com/paper/2409.18418/) (2024)
- [Learning from Limited and Imperfect Data](https://mlsanity.com/paper/2411.07229/) (2024)
- [Learning from Limited and Imperfect Data](https://mlsanity.com/paper/2507.21205/) (2025)

## Abstract (arXiv)

Unsupervised domain adaptation (DA) methods have focused on achieving maximal performance through aligning features from source and target domains without using labeled data in the target domain. Whereas, in the real-world scenario's it might be feasible to get labels for a small proportion of target data. In these scenarios, it is important to select maximally-informative samples to label and find an effective way to combine them with the existing knowledge from source data. Towards achieving this, we propose S3VAADA which i) introduces a novel submodular criterion to select a maximally informative subset to label and ii) enhances a cluster-based DA procedure through novel improvements to effectively utilize all the available data for improving generalization on target. Our approach consistently outperforms the competing state-of-the-art approaches on datasets with varying degrees of domain shifts.