mlsanityData to 7 Oct 2026

S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation

arXiv 2109.08901 ↗First posted 18 Sep 2021cs.LG cs.AI cs.CVcited by 19

Not on the map. Why?

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.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 27 of its 48 references that are in the map. First posted on arXiv 18 Sep 2021.

Builds on

27 of 48 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  4. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  5. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  7. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  8. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  9. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  10. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  11. 2019Learning Loss for Active Learningcited by 335
  12. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 333
15 more
  1. 2019Variational Adversarial Active Learningcited by 284
  2. 2020Universal Source-Free Domain Adaptationcited by 219
  3. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  4. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 155
  5. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  6. 2020Cross-domain Detection via Graph-induced Prototype Alignmentcited by 109
  7. 2017Adversarial Dropout Regularizationcited by 106
  8. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88
  9. 2019Active Adversarial Domain Adaptationcited by 73
  10. 2020Active Domain Adaptation via Clustering Uncertainty-weighted Embeddingscited by 71
  11. 2020Adversarial-Learned Loss for Domain Adaptationcited by 65
  12. 2020Towards Inheritable Models for Open-Set Domain Adaptationcited by 64
  13. 2020Online Meta-Learning for Multi-Source and Semi-Supervised Domain Adaptationcited by 64
  14. 2019Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptationcited by 62
  15. 2019Submodular Batch Selection for Training Deep Neural Networkscited by 7

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 8; 2023: 3; 2024: 5; 2025: 2.

19 papers.

Sort:

  1. 2022A Closer Look at Smoothness in Domain Adversarial Trainingcited by 85
  2. 2022Balancing Discriminability and Transferability for Source-Free Domain Adaptationcited by 58
  3. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 56
  4. 2023A comprehensive survey on deep active learning in medical image analysiscited by 32
  5. 2022Learning Distinctive Margin toward Active Domain Adaptationcited by 18
  6. 2022Combating Label Distribution Shift for Active Domain Adaptationcited by 14
  7. 2024Contributing Dimension Structure of Deep Feature for Coreset Selectioncited by 5
  8. 2022Local Context-Aware Active Domain Adaptationcited by 4
  9. 2023Spectral Transfer Guided Active Domain Adaptation For Thermal Imagerycited by 3
  10. 2025Certainty and Uncertainty Guided Active Domain Adaptationcited by 3
  11. 2024Domain Adversarial Active Learning for Domain Generalization Classificationcited by 2
  12. 2022Loss-based Sequential Learning for Active Domain Adaptationcited by 1
7 more
  1. 2022Scalable Distributed Algorithms for Size-Constrained Submodular Maximization in the MapReduce and Adaptive Complexity Modelscited by 1
  2. 2024D3GU: Multi-Target Active Domain Adaptation via Enhancing Domain Alignmentcited by 1
  3. 2022Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shiftcited by 0
  4. 2023Score-Based Methods for Discrete Optimization in Deep Learningcited by 0
  5. 2024A3: Active Adversarial Alignment for Source-Free Domain Adaptationcited by 0
  6. 2024Learning from Limited and Imperfect Datacited by 0
  7. 2025Learning from Limited and Imperfect Datacited by 0