mlsanityData to 7 Oct 2026

Curriculum Manager for Source Selection in Multi-Source Domain Adaptation

arXiv 2007.01261 ↗First posted 2 Jul 2020cs.CV cs.LG eess.IVcited by 55

Not on the map. Why?

Abstract (arXiv)

The performance of Multi-Source Unsupervised Domain Adaptation depends significantly on the effectiveness of transfer from labeled source domain samples. In this paper, we proposed an adversarial agent that learns a dynamic curriculum for source samples, called Curriculum Manager for Source Selection (CMSS). The Curriculum Manager, an independent network module, constantly updates the curriculum during training, and iteratively learns which domains or samples are best suited for aligning to the target. The intuition behind this is to force the Curriculum Manager to constantly re-measure the transferability of latent domains over time to adversarially raise the error rate of the domain discriminator. CMSS does not require any knowledge of the domain labels, yet it outperforms other methods on four well-known benchmarks by significant margins. We also provide interpretable results that shed light on the proposed method.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 11; 2023: 10; 2024: 5; 2025: 5; 2026: 2.

55 papers.

Sort:

By area:

  1. 2021Domain Generalization: A Surveycited by 760
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2021DINE: Domain Adaptation from Single and Multiple Black-box Predictorscited by 51
  4. 2022Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Expertscited by 50
  5. 2021Curriculum Graph Co-Teaching for Multi-Target Domain Adaptationcited by 37
  6. 2023Subspace Identification for Multi-Source Domain Adaptationcited by 36
  7. 2021ToAlign: Task-oriented Alignment for Unsupervised Domain Adaptationcited by 33
  8. 2021A Style and Semantic Memory Mechanism for Domain Generalizationcited by 32
  9. 2021Unsupervised Multi-Source Domain Adaptation for Person Re-Identificationcited by 30
  10. 2021Dynamic Transfer for Multi-Source Domain Adaptationcited by 29
  11. 2022Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domaincited by 27
  12. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
38 more
  1. 2023MADG: Margin-based Adversarial Learning for Domain Generalizationcited by 22
  2. 2021Multi-Source Domain Adaptation for Object Detectioncited by 21
  3. 2021Memory-aware curriculum federated learning for breast cancer classificationcited by 20
  4. 2021Multi-Source Video Domain Adaptation with Temporal Attentive Moment Alignmentcited by 20
  5. 2021Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Surveycited by 19
  6. 2023Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identificationcited by 16
  7. 2021Contrastive Vicinal Space for Unsupervised Domain Adaptationcited by 14
  8. 2021Transferrable Contrastive Learning for Visual Domain Adaptationcited by 14
  9. 2023Partial Identifiability for Domain Adaptationcited by 14
  10. 2021Re-energizing Domain Discriminator with Sample Relabeling for Adversarial Domain Adaptationcited by 12
  11. 2021Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularizationcited by 12
  12. 2022Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptationcited by 12
  13. 2021Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptationcited by 10
  14. 2022Learning to Learn: How to Continuously Teach Humans and Machinescited by 9
  15. 2024More is Better: Deep Domain Adaptation with Multiple Sourcescited by 9
  16. 2024M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Trainingcited by 8
  17. 2021Graphical Modeling for Multi-Source Domain Adaptationcited by 7
  18. 2023Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentationcited by 7
  19. 2024Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scenecited by 7
  20. 2022Dynamic Instance Domain Adaptationcited by 6
  21. 2025Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognitioncited by 6
  22. 2022Self-Supervised Graph Neural Network for Multi-Source Domain Adaptationcited by 5
  23. 2022Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptationcited by 5
  24. 2021Adaptive Pseudo-Label Refinement by Negative Ensemble Learning for Source-Free Unsupervised Domain Adaptationcited by 4
  25. 2021Domain Attention Consistency for Multi-Source Domain Adaptationcited by 4
  26. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  27. 2024Multi-source Unsupervised Domain Adaptation on Graphs with Transferability Modelingcited by 4
  28. 2021Burn After Reading: Online Adaptation for Cross-domain Streaming Datacited by 3
  29. 2022Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifierscited by 3
  30. 2022Robust Target Training for Multi-Source Domain Adaptationcited by 3
  31. 2021SHIFT15M: Fashion-specific dataset for set-to-set matching with several distribution shiftscited by 2
  32. 2024SepRep-Net: Multi-source Free Domain Adaptation via Model Separation And Reparameterizationcited by 2
  33. 2025SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptationcited by 2
  34. 2025Low-Rank Expert Merging for Multi-Source Domain Adaptation in Person Re-Identificationcited by 2
  35. 2026A General Representation-Based Approach to Multi-Source Domain Adaptationcited by 2
  36. 2023Generative Model Based Noise Robust Training for Unsupervised Domain Adaptationcited by 1
  37. 2023Continual Source-Free Unsupervised Domain Adaptationcited by 1
  38. 2023Adapt Anything: Tailor Any Image Classifiers across Domains And Categories Using Text-to-Image Diffusion Modelscited by 1

50 most cited of 55 All 55 (JSON)