mlsanityData to 7 Oct 2026

DMSD-CDFSAR: Distillation from Mixed-Source Domain for Cross-Domain Few-shot Action Recognition

arXiv 2407.05657 ↗First posted 8 Jul 2024cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Few-shot action recognition is an emerging field in computer vision, primarily focused on meta-learning within the same domain. However, challenges arise in real-world scenario deployment, as gathering extensive labeled data within a specific domain is laborious and time-intensive. Thus, attention shifts towards cross-domain few-shot action recognition, requiring the model to generalize across domains with significant deviations. Therefore, we propose a novel approach, ``Distillation from Mixed-Source Domain", tailored to address this conundrum. Our method strategically integrates insights from both labeled data of the source domain and unlabeled data of the target domain during the training. The ResNet18 is used as the backbone to extract spatial features from the source and target domains. We design two branches for meta-training: the original-source and the mixed-source branches. In the first branch, a Domain Temporal Encoder is employed to capture temporal features for both the source and target domains. Additionally, a Domain Temporal Decoder is employed to reconstruct all extracted features. In the other branch, a Domain Mixed Encoder is used to handle labeled source domain data and unlabeled target domain data, generating mixed-source domain features. We incorporate a pre-training stage before meta-training, featuring a network architecture similar to that of the first branch. Lastly, we introduce a dual distillation mechanism to refine the classification probabilities of source domain features, aligning them with those of mixed-source domain features. This iterative process enriches the insights of the original-source branch with knowledge from the mixed-source branch, thereby enhancing the model's generalization capabilities. Our code is available at URL: urlhttps://xxxx/xxxx/xxxx.git

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 34 of its 62 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

34 of 62 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  6. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,092
  11. 2016Temporal Segment Networks: Towards Good Practices for Deep Action Recognitioncited by 899
  12. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
22 more
  1. 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 368
  2. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  3. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
  4. 2016Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptationcited by 162
  5. 2019Few-Shot Video Classification via Temporal Alignmentcited by 124
  6. 2017Learning to Compose Domain-Specific Transformations for Data Augmentationcited by 91
  7. 2021Temporal-Relational CrossTransformers for Few-Shot Action Recognitioncited by 83
  8. 2020Self-training for Few-shot Transfer Across Extreme Task Differencescited by 75
  9. 2019TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognitioncited by 71
  10. 2021Spatio-temporal Relation Modeling for Few-shot Action Recognitioncited by 52
  11. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  12. 2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
  13. 2020Multimodal Prototypical Networks for Few-shot Learningcited by 48
  14. 2019ProtoGAN: Towards Few Shot Learning for Action Recognitioncited by 41
  15. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  16. 2020RareAct: A video dataset of unusual interactionscited by 23
  17. 2021Few-Shot Action Recognition with Compromised Metric via Optimal Transportcited by 12
  18. 2023CDFSL-V: Cross-Domain Few-Shot Learning for Videoscited by 12
  19. 2021Cross-domain few-shot learning with unlabelled datacited by 10
  20. 2022Hierarchical Compositional Representations for Few-shot Action Recognitioncited by 10
  21. 2023Task-Specific Alignment and Multiple Level Transformer for Few-Shot Action Recognitioncited by 2
  22. 2023Adaptive Semantic Consistency for Cross-domain Few-shot Classificationcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 1.

3 papers.

  1. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  2. 2024TAMT: Temporal-Aware Model Tuning for Cross-Domain Few-Shot Action Recognitioncited by 3
  3. 2025Modality-Collaborative Low-Rank Decomposers for Few-Shot Video Domain Adaptationcited by 0