mlsanityData to 14 Oct 2026

A Comprehensive Survey of Challenges and Opportunities of Few-Shot Learning Across Multiple Domains

arXiv 2504.04017 ↗First posted 5 Apr 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In a world where new domains are constantly discovered and machine learning (ML) is applied to automate new tasks every day, challenges arise with the number of samples available to train ML models. While the traditional ML training relies heavily on data volume, finding a large dataset with a lot of usable samples is not always easy, and often the process takes time. For instance, when a new human transmissible disease such as COVID-19 breaks out and there is an immediate surge for rapid diagnosis, followed by rapid isolation of infected individuals from healthy ones to contain the spread, there is an immediate need to create tools/automation using machine learning models. At the early stage of an outbreak, it is not only difficult to obtain a lot of samples, but also difficult to understand the details about the disease, to process the data needed to train a traditional ML model. A solution for this can be a few-shot learning approach. This paper presents challenges and opportunities of few-shot approaches that vary across major domains, i.e., audio, image, text, and their combinations, with their strengths and weaknesses. This detailed understanding can help to adopt appropriate approaches applicable to different domains and applications.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 84 of its 214 references that are in the map. First posted on arXiv 5 Apr 2025.

Builds on

84 of 214 references.

References · 84

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  5. 2019A Closer Look at Few-shot Classificationcited by 684
  6. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  7. 2019A Baseline for Few-Shot Image Classificationcited by 298
  8. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  9. 2022LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learningcited by 230
  10. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 168
  11. 2023AugGPT: Leveraging ChatGPT for Text Data Augmentationcited by 130
  12. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
38 more
  1. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
  2. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  3. 2022Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learningcited by 58
  4. 2020Few-Shot Open-Set Recognition using Meta-Learningcited by 50
  5. 2019A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classificationcited by 45
  6. 2019Self-Supervised Learning For Few-Shot Image Classificationcited by 44
  7. 2023UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modelingcited by 40
  8. 2017Transfer learning for music classification and regression taskscited by 37
  9. 2022GPS: Genetic Prompt Search for Efficient Few-shot Learningcited by 37
  10. 2021Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learningcited by 35
  11. 2022Few-shot Medical Image Segmentation with Cycle-resemblance Attentioncited by 33
  12. 2021FlipDA: Effective and Robust Data Augmentation for Few-Shot Learningcited by 32
  13. 2019Few-Shot Representation Learning for Out-Of-Vocabulary Wordscited by 30
  14. 2023Log Parsing with Prompt-based Few-shot Learningcited by 29
  15. 2021Few-Shot Keyword Spotting in Any Languagecited by 27
  16. 2021Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifierscited by 24
  17. 2022MetaAudio: A Few-Shot Audio Classification Benchmarkcited by 24
  18. 2021Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speechcited by 22
  19. 2020RS-MetaNet: Deep meta metric learning for few-shot remote sensing scene classificationcited by 19
  20. 2019A Two-Stage Approach to Few-Shot Learning for Image Recognitioncited by 18
  21. 2023Self-Sampling Meta SAM: Enhancing Few-shot Medical Image Segmentation with Meta-Learningcited by 18
  22. 2021AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentationcited by 17
  23. 2023Making Scalable Meta Learning Practicalcited by 17
  24. 2019Revisiting Metric Learning for Few-Shot Image Classificationcited by 14
  25. 2021Memory Efficient Meta-Learning with Large Imagescited by 14
  26. 2023Learning to detect an animal sound from five examplescited by 14
  27. 2018Learning to match transient sound events using attentional similarity for few-shot sound recognitioncited by 13
  28. 2020Few-shot acoustic event detection via meta-learningcited by 13
  29. 2023Cross-Modal Concept Learning and Inference for Vision-Language Modelscited by 12
  30. 2021Who calls the shots? Rethinking Few-Shot Learning for Audiocited by 11
  31. 2022Prompt-Learning for Short Text Classificationcited by 11
  32. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  33. 2022Active Few-Shot Learning with FASLcited by 11
  34. 2019Few-shot Learning for Domain-specific Fine-grained Image Classificationcited by 10
  35. 2021MetaDelta: A Meta-Learning System for Few-shot Image Classificationcited by 10
  36. 2023Adapting Language-Audio Models as Few-Shot Audio Learnerscited by 10
  37. 2018Training neural audio classifiers with few datacited by 9
  38. 2021ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classificationcited by 8

50 most cited of 84 All 84 (JSON)

Built on by

Not cited yet.