mlsanityData to 13 Oct 2026

On the Effectiveness of Image Rotation for Open Set Domain Adaptation

arXiv 2007.12360 ↗First posted 24 Jul 2020cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source. To avoid negative transfer, OSDA can be tackled by first separating the known/unknown target samples and then aligning known target samples with the source data. We propose a novel method to addresses both these problems using the self-supervised task of rotation recognition. Moreover, we assess the performance with a new open set metric that properly balances the contribution of recognizing the known classes and rejecting the unknown samples. Comparative experiments with existing OSDA methods on the standard Office-31 and Office-Home benchmarks show that: (i) our method outperforms its competitors, (ii) reproducibility for this field is a crucial issue to tackle, (iii) our metric provides a reliable tool to allow fair open set evaluation.

Key facts. Cited by 72 papers in the map (data through 13 Oct 2026). First posted on arXiv 24 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 10; 2022: 18; 2023: 19; 2024: 16; 2025: 7; 2026: 2.

72 papers.

Sort:

By area:

  1. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 94
  2. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  3. 2022Unified Optimal Transport Framework for Universal Domain Adaptationcited by 57
  4. 2022Domain Adaptation under Open Set Label Shiftcited by 32
  5. 2023Upcycling Models under Domain and Category Shiftcited by 29
  6. 2022Source-Free Progressive Graph Learning for Open-Set Domain Adaptationcited by 25
  7. 2021UMAD: Universal Model Adaptation under Domain and Category Shiftcited by 23
  8. 2022Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptationcited by 21
  9. 2024Your Data Is Not Perfect: Towards Cross-Domain Out-of-Distribution Detection in Class-Imbalanced Datacited by 21
  10. 2024Unknown Prompt, the only Lacuna: Unveiling CLIP's Potential for Open Domain Generalizationcited by 20
  11. 2022Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifiercited by 18
  12. 2023AutoLabel: CLIP-based framework for Open-set Video Domain Adaptationcited by 18
38 more
  1. 2022Subsidiary Prototype Alignment for Universal Domain Adaptationcited by 17
  2. 2024Towards Multimodal Open-Set Domain Generalization and Adaptation through Self-supervisioncited by 16
  3. 2023Universal Domain Adaptation via Compressive Attention Matchingcited by 15
  4. 2024PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalizationcited by 15
  5. 2021Towards Novel Target Discovery Through Open-Set Domain Adaptationcited by 13
  6. 2024Open-Set Domain Adaptation for Semantic Segmentationcited by 13
  7. 2021Generalized Domain Adaptationcited by 10
  8. 2021Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptationcited by 10
  9. 2023Open-Set Domain Adaptation with Visual-Language Foundation Modelscited by 10
  10. 2021Conditional Extreme Value Theory for Open Set Video Domain Adaptationcited by 9
  11. 2021Progressively Select and Reject Pseudo-labelled Samples for Open-Set Domain Adaptationcited by 9
  12. 2023Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignmentcited by 9
  13. 2023Activate and Reject: Towards Safe Domain Generalization under Category Shiftcited by 9
  14. 2022Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptationcited by 8
  15. 2023DEVIAS: Learning Disentangled Video Representations of Action and Scenecited by 7
  16. 2024Prototypical Partial Optimal Transport for Universal Domain Adaptationcited by 7
  17. 2023Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptationcited by 6
  18. 2024Recall and Refine: A Simple but Effective Source-free Open-set Domain Adaptation Frameworkcited by 6
  19. 2022Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptationcited by 5
  20. 2022Exploiting Inter-Sample Affinity for Knowability-Aware Universal Domain Adaptationcited by 5
  21. 2023Unknown Sample Discovery for Source Free Open Set Domain Adaptationcited by 5
  22. 2024COSMo: CLIP Talks on Open-Set Multi-Target Domain Adaptationcited by 5
  23. 2021Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layerscited by 4
  24. 2024GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learningcited by 4
  25. 2024Memory-Efficient Pseudo-Labeling for Online Source-Free Universal Domain Adaptation using a Gaussian Mixture Modelcited by 4
  26. 2025Open-set Cross Modal Generalization via Multimodal Unified Representationcited by 4
  27. 2022IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptationcited by 3
  28. 2023COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptationcited by 3
  29. 2024Bridging OOD Detection and Generalization: A Graph-Theoretic Viewcited by 3
  30. 2022Learning from Synthetic InSAR with Vision Transformers: The case of volcanic unrest detectioncited by 2
  31. 2022OneRing: A Simple Method for Source-free Open-partial Domain Adaptationcited by 2
  32. 2022Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradoxcited by 2
  33. 2022Semantic Novelty Detection via Relational Reasoningcited by 2
  34. 2023Self-Paced Learning for Open-Set Domain Adaptationcited by 2
  35. 2023Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitationcited by 2
  36. 2023Mixture-of-Experts for Open Set Domain Adaptation: A Dual-Space Detection Approachcited by 2
  37. 2023A Unified Framework for Unsupervised Domain Adaptation based on Instance Weightingcited by 2
  38. 2024COMET: Contrastive Mean Teacher for Online Source-Free Universal Domain Adaptationcited by 2

50 most cited of 72 All 72 (JSON)