mlsanityData to 7 Oct 2026

Adaptive Cross-Modal Few-Shot Learning

arXiv 1902.07104 ↗First posted 19 Feb 2019cs.LG stat.MLcited by 95

Not on the map. Why?

Abstract (arXiv)

Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, visual features might be richer and more discriminative than text ones. While for others, the inverse might be true. Moreover, when the support from visual information is limited in image classification, semantic representations (learned from unsupervised text corpora) can provide strong prior knowledge and context to help learning. Based on these two intuitions, we propose a mechanism that can adaptively combine information from both modalities according to new image categories to be learned. Through a series of experiments, we show that by this adaptive combination of the two modalities, our model outperforms current uni-modality few-shot learning methods and modality-alignment methods by a large margin on all benchmarks and few-shot scenarios tested. Experiments also show that our model can effectively adjust its focus on the two modalities. The improvement in performance is particularly large when the number of shots is very small.

Key facts. Cited by 95 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 23; 2023: 19; 2024: 17; 2025: 9; 2026: 4.

95 papers.

Sort:

By area:

  1. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  2. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  3. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  4. 2021MultiBench: Multiscale Benchmarks for Multimodal Representation Learningcited by 143
  5. 2022Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questionscited by 116
  6. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115
  7. 2023Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Modelscited by 91
  8. 2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
  9. 2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
  10. 2023CLIP-guided Prototype Modulating for Few-shot Action Recognitioncited by 41
  11. 2021Few-Shot Object Detection via Association and DIscriminationcited by 39
  12. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
38 more
  1. 2022SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classificationcited by 34
  2. 2022High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learningcited by 31
  3. 2022Few-Shot Classification with Contrastive Learningcited by 31
  4. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  5. 2024Codebook Transfer with Part-of-Speech for Vector-Quantized Image Modelingcited by 16
  6. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  7. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  8. 2021Rich Semantics Improve Few-shot Learningcited by 15
  9. 2021SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learningcited by 15
  10. 2021Inferring Prototypes for Multi-Label Few-Shot Image Classification with Word Vector Guided Attentioncited by 15
  11. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  12. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  13. 2021Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learningcited by 12
  14. 2023FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learningcited by 12
  15. 2021Audio-to-Image Cross-Modal Generationcited by 11
  16. 2021Multimodality in Meta-Learning: A Comprehensive Surveycited by 11
  17. 2022Multi-Modal Few-Shot Object Detection with Meta-Learning-Based Cross-Modal Promptingcited by 11
  18. 2022Modelling Commonsense Properties using Pre-Trained Bi-Encoderscited by 9
  19. 2025Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learningcited by 9
  20. 2021HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalitiescited by 8
  21. 2023Distilling Semantic Concept Embeddings from Contrastively Fine-Tuned Language Modelscited by 8
  22. 2023Ultra-Fine Entity Typing with Prior Knowledge about Labels: A Simple Clustering Based Strategycited by 8
  23. 2023Episodic Multi-Task Learning with Heterogeneous Neural Processescited by 8
  24. 2024Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learningcited by 8
  25. 2021Prototype Completion for Few-Shot Learningcited by 7
  26. 2024Making Large Vision Language Models to be Good Few-shot Learnerscited by 7
  27. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  28. 2021Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learningcited by 6
  29. 2021MHFC: Multi-Head Feature Collaboration for Few-Shot Learningcited by 6
  30. 2022Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptionscited by 6
  31. 2021Contextualizing Meta-Learning via Learning to Decomposecited by 5
  32. 2021MDFM: Multi-Decision Fusing Model for Few-Shot Learningcited by 5
  33. 2022GCT: Graph Co-Training for Semi-Supervised Few-Shot Learningcited by 5
  34. 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
  35. 2022Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learningcited by 4
  36. 2022Brainish: Formalizing A Multimodal Language for Intelligence and Consciousnesscited by 4
  37. 2022Kernel Relative-prototype Spectral Filtering for Few-shot Learningcited by 4
  38. 2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4

50 most cited of 95 All 95 (JSON)