mlsanityData to 7 Oct 2026

Few-Shot Learning via Saliency-guided Hallucination of Samples

arXiv 1904.03472 ↗First posted 6 Apr 2019cs.CVcited by 49

Not on the map. Why?

Abstract (arXiv)

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) generating or hallucinating additional data from the limited existing samples. In this paper, we follow the latter direction and present a novel data hallucination model. Currently, most datapoint generators contain a specialized network (i.e., GAN) tasked with hallucinating new datapoints, thus requiring large numbers of annotated data for their training in the first place. In this paper, we propose a novel less-costly hallucination method for few-shot learning which utilizes saliency maps. To this end, we employ a saliency network to obtain the foregrounds and backgrounds of available image samples and feed the resulting maps into a two-stream network to hallucinate datapoints directly in the feature space from viable foreground-background combinations. To the best of our knowledge, we are the first to leverage saliency maps for such a task and we demonstrate their usefulness in hallucinating additional datapoints for few-shot learning. Our proposed network achieves the state of the art on publicly available datasets.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 8; 2023: 11; 2024: 3; 2025: 2; 2026: 2.

49 papers.

Sort:

  1. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  2. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  3. 2022Spectral Feature Augmentation for Graph Contrastive Learning and Beyondcited by 49
  4. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  5. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  6. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  7. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  8. 2021Transductive Few-Shot Classification on the Oblique Manifoldcited by 23
  9. 2021Meta-Learning for Multi-Label Few-Shot Classificationcited by 21
  10. 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
  11. 2023Hallucination Improves the Performance of Unsupervised Visual Representation Learningcited by 16
  12. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
37 more
  1. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  2. 2022Multi-level Second-order Few-shot Learningcited by 12
  3. 2022Learnable Distribution Calibration for Few-Shot Class-Incremental Learningcited by 12
  4. 2021Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learningcited by 11
  5. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  6. 2023Few-shot Action Recognition with Captioning Foundation Modelscited by 9
  7. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  8. 2023From Saliency to DINO: Saliency-guided Vision Transformer for Few-shot Keypoint Detectioncited by 8
  9. 2023GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensingcited by 8
  10. 2024Dense Vision Transformer Compression with Few Samplescited by 8
  11. 2021Tensor feature hallucination for few-shot learningcited by 6
  12. 2021Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learningcited by 6
  13. 2023Learning Partial Correlation based Deep Visual Representation for Image Classificationcited by 6
  14. 2023Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognitioncited by 6
  15. 2023Mitigating the Effect of Incidental Correlations on Part-based Learningcited by 6
  16. 2021Local Propagation for Few-Shot Learningcited by 4
  17. 2021Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognitioncited by 4
  18. 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
  19. 2021Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decompositioncited by 4
  20. 2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
  21. 2021Few-shot Partial Multi-view Learningcited by 3
  22. 2025Feature Hallucination for Self-supervised Action Recognitioncited by 3
  23. 2021Machine learning with limited datacited by 2
  24. 2021Few-shot learning via tensor hallucinationcited by 1
  25. 2021A Strong Baseline for Semi-Supervised Incremental Few-Shot Learningcited by 1
  26. 2023RAFIC: Retrieval-Augmented Few-shot Image Classificationcited by 1
  27. 2024Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognitioncited by 1
  28. 2024Controllable Relation Disentanglement for Few-Shot Class-Incremental Learningcited by 1
  29. 2025Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancementcited by 1
  30. 2026EfficientFSL: Enhancing Few-Shot Classification via Query-Only Tuning in Vision Transformerscited by 1
  31. 2021Distance Metric-Based Learning with Interpolated Latent Features for Location Classification in Endoscopy Image and Videocited by 0
  32. 2021CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognitioncited by 0
  33. 2021Few-shot Learning with Global Relatedness Decoupled-Distillationcited by 0
  34. 2021Dual Path Structural Contrastive Embeddings for Learning Novel Objectscited by 0
  35. 2022Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognitioncited by 0
  36. 2023Few-shot Multispectral Segmentation with Representations Generated by Reinforcement Learningcited by 0
  37. 2026IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learningcited by 0