mlsanityData to 7 Oct 2026

Towards Novel Target Discovery Through Open-Set Domain Adaptation

arXiv 2105.02432 ↗First posted 6 May 2021cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Open-set domain adaptation (OSDA) considers that the target domain contains samples from novel categories unobserved in external source domain. Unfortunately, existing OSDA methods always ignore the demand for the information of unseen categories and simply recognize them as "unknown" set without further explanation. This motivates us to understand the unknown categories more specifically by exploring the underlying structures and recovering their interpretable semantic attributes. In this paper, we propose a novel framework to accurately identify the seen categories in target domain, and effectively recover the semantic attributes for unseen categories. Specifically, structure preserving partial alignment is developed to recognize the seen categories through domain-invariant feature learning. Attribute propagation over visual graph is designed to smoothly transit attributes from seen to unseen categories via visual-semantic mapping. Moreover, two new cross-main benchmarks are constructed to evaluate the proposed framework in the novel and practical challenge. Experimental results on open-set recognition and semantic recovery demonstrate the superiority of the proposed method over other compared baselines.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 41 of its 61 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

41 of 61 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  5. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  6. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  7. 2015Label-Embedding for Image Classificationcited by 164
  8. 2018Open Set Domain Adaptation by Backpropagationcited by 150
  9. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  10. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  11. 2020Unsupervised Domain Adaptation via Structurally Regularized Deep Clusteringcited by 140
  12. 2020Gradually Vanishing Bridge for Adversarial Domain Adaptationcited by 130
29 more
  1. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  2. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  3. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
  4. 2019Discriminative Adversarial Domain Adaptationcited by 74
  5. 2020On the Effectiveness of Image Rotation for Open Set Domain Adaptationcited by 72
  6. 2020Adversarial-Learned Loss for Domain Adaptationcited by 65
  7. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  8. 2020Towards Inheritable Models for Open-Set Domain Adaptationcited by 64
  9. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  10. 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
  11. 2020Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptationcited by 60
  12. 2020Progressive Graph Learning for Open-Set Domain Adaptationcited by 56
  13. 2019Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learningcited by 38
  14. 2019Transductive Zero-Shot Learning with Visual Structure Constraintcited by 36
  15. 2020Label Propagation with Augmented Anchors: A Simple Semi-Supervised Learning baseline for Unsupervised Domain Adaptationcited by 35
  16. 2020A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learningcited by 34
  17. 2019Creativity Inspired Zero-Shot Learningcited by 27
  18. 2020Exploring Category-Agnostic Clusters for Open-Set Domain Adaptationcited by 27
  19. 2020Bi-Directional Generation for Unsupervised Domain Adaptationcited by 26
  20. 2020CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptationcited by 23
  21. 2017Zero-Shot Learning via Class-Conditioned Deep Generative Modelscited by 21
  22. 2019Zero-shot Learning via Simultaneous Generating and Learningcited by 17
  23. 2018Learning Factorized Representations for Open-set Domain Adaptationcited by 13
  24. 2019Attract or Distract: Exploit the Margin of Open Setcited by 13
  25. 2019Unsupervised Open Domain Recognition by Semantic Discrepancy Minimizationcited by 10
  26. 2020Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptationcited by 9
  27. 2019Weakly Supervised Open-set Domain Adaptation by Dual-domain Collaborationcited by 8
  28. 2019EV-Action: Electromyography-Vision Multi-Modal Action Datasetcited by 4
  29. 2020Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 5; 2024: 2; 2025: 1; 2026: 1.

13 papers.

Sort:

  1. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  2. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  3. 2023MLNet: Mutual Learning Network with Neighborhood Invariance for Universal Domain Adaptationcited by 14
  4. 2022Learning with Style: Continual Semantic Segmentation Across Tasks and Domainscited by 9
  5. 2024Cross-domain Open-world Discoverycited by 6
  6. 2024Exclusive Style Removal for Cross Domain Novel Class Discoverycited by 5
  7. 2022OneRing: A Simple Method for Source-free Open-partial Domain Adaptationcited by 2
  8. 2023Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discoverycited by 2
  9. 2023Trustworthy Representation Learning Across Domainscited by 1
  10. 2023Open Set Dandelion Network for IoT Intrusion Detectioncited by 1
  11. 2021Reiterative Domain Aware Multi-Target Adaptationcited by 0
  12. 2025Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learningcited by 0
1 more
  1. 2026DeFed-GMM-DaDiL: A Decentralized Federated Framework for Domain Adaptationcited by 0