mlsanityData to 7 Oct 2026

Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning

arXiv 2403.01966 ↗First posted 4 Mar 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Existing Cross-Domain Few-Shot Learning (CDFSL) methods require access to source domain data to train a model in the pre-training phase. However, due to increasing concerns about data privacy and the desire to reduce data transmission and training costs, it is necessary to develop a CDFSL solution without accessing source data. For this reason, this paper explores a Source-Free CDFSL (SF-CDFSL) problem, in which CDFSL is addressed through the use of existing pretrained models instead of training a model with source data, avoiding accessing source data. This paper proposes an Enhanced Information Maximization with Distance-Aware Contrastive Learning (IM-DCL) method to address these challenges. Firstly, we introduce the transductive mechanism for learning the query set. Secondly, information maximization (IM) is explored to map target samples into both individual certainty and global diversity predictions, helping the source model better fit the target data distribution. However, IM fails to learn the decision boundary of the target task. This motivates us to introduce a novel approach called Distance-Aware Contrastive Learning (DCL), in which we consider the entire feature set as both positive and negative sets, akin to Schrodinger's concept of a dual state. Instead of a rigid separation between positive and negative sets, we employ a weighted distance calculation among features to establish a soft classification of the positive and negative sets for the entire feature set. Furthermore, we address issues related to IM by incorporating contrastive constraints between object features and their corresponding positive and negative sets. Evaluations of the 4 datasets in the BSCD-FSL benchmark indicate that the proposed IM-DCL, without accessing the source domain, demonstrates superiority over existing methods, especially in the distant domain task.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 49 of its 71 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

49 of 71 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2022Visual Prompt Tuningcited by 1,674
  8. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,488
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  11. 2020Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptationcited by 844
  12. 2019Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)cited by 657
37 more
  1. 2020A Survey on Visual Transformercited by 653
  2. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  3. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 216
  4. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  5. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  6. 2021Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptationcited by 176
  7. 2021Generalized Source-free Domain Adaptationcited by 175
  8. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  9. 2017Learning Discrete Representations via Information Maximizing Self-Augmented Trainingcited by 149
  10. 2013Learning by Transductioncited by 120
  11. 2022Source-Free Domain Adaptation via Distribution Estimationcited by 97
  12. 2017PatternNet: A Benchmark Dataset for Performance Evaluation of Remote Sensing Image Retrievalcited by 96
  13. 2022Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptationcited by 93
  14. 2020Domain Adaptation with Auxiliary Target Domain-Oriented Classifiercited by 76
  15. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  16. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  17. 2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
  18. 2020Explanation-Guided Training for Cross-Domain Few-Shot Classificationcited by 58
  19. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  20. 2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
  21. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  22. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  23. 2022Uncertainty-guided Source-free Domain Adaptationcited by 46
  24. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  25. 2021Ranking Distance Calibration for Cross-Domain Few-Shot Learningcited by 27
  26. 2022Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classificationcited by 25
  27. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  28. 2020Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classificationcited by 20
  29. 2023Dual Adaptive Representation Alignment for Cross-domain Few-shot Learningcited by 15
  30. 2023Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Surveycited by 14
  31. 2022Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptationcited by 13
  32. 2022Efficient Few-Shot Object Detection via Knowledge Inheritancecited by 12
  33. 2022FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classificationcited by 9
  34. 2022ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learningcited by 6
  35. 2023Instance-level Few-shot Learning with Class Hierarchy Miningcited by 5
  36. 2022Cross-Domain Few-Shot Classification via Inter-Source Stylizationcited by 4
  37. 2023Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classificationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 5.

13 papers.

Sort:

By area:

  1. 2024Towards Few-Shot Learning in the Open World: A Review and Beyondcited by 5
  2. 2024Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learningcited by 5
  3. 2026Reclaiming Lost Text Layers for Source-Free Cross-Domain Few-Shot Learningcited by 5
  4. 2025Random Registers for Cross-Domain Few-Shot Learningcited by 4
  5. 2026Mind the Discriminability Trap in Source-Free Cross-domain Few-shot Learningcited by 4
  6. 2026Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignmentcited by 4
  7. 2025Few-Shot Vision-Language Action-Incremental Policy Learningcited by 3
  8. 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learningcited by 3
  9. 2025Cross-Domain Few-Shot Learning with Coalescent Projections and Latent Space Reservationcited by 2
  10. 2026Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learningcited by 2
  11. 2025Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddingscited by 1
  12. 2026Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learningcited by 1
1 more
  1. 2025AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Imagescited by 0