mlsanityData to 7 Oct 2026

Image Deformation Meta-Networks for One-Shot Learning

arXiv 1905.11641 ↗First posted 28 May 2019cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

Humans can robustly learn novel visual concepts even when images undergo various deformations and lose certain information. Mimicking the same behavior and synthesizing deformed instances of new concepts may help visual recognition systems perform better one-shot learning, i.e., learning concepts from one or few examples. Our key insight is that, while the deformed images may not be visually realistic, they still maintain critical semantic information and contribute significantly to formulating classifier decision boundaries. Inspired by the recent progress of meta-learning, we combine a meta-learner with an image deformation sub-network that produces additional training examples, and optimize both models in an end-to-end manner. The deformation sub-network learns to deform images by fusing a pair of images --- a probe image that keeps the visual content and a gallery image that diversifies the deformations. We demonstrate results on the widely used one-shot learning benchmarks (miniImageNet and ImageNet 1K Challenge datasets), which significantly outperform state-of-the-art approaches. Code is available at https://github.com/tankche1/IDeMe-Net.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 14; 2023: 9; 2024: 5; 2025: 9; 2026: 1.

56 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  2. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  3. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  4. 2021Meta-Learning with Fewer Tasks through Task Interpolationcited by 45
  5. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  6. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
  7. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  8. 2023MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognitioncited by 26
  9. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  10. 2024MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognitioncited by 25
  11. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  12. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
38 more
  1. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  2. 2024Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedycited by 13
  3. 2021Semantic Compositional Learning for Low-shot Scene Graph Generationcited by 12
  4. 2021Few-Shot Learning by Integrating Spatial and Frequency Representationcited by 11
  5. 2021Boosting Few-Shot Classification with View-Learnable Contrastive Learningcited by 11
  6. 2021Multimodality in Meta-Learning: A Comprehensive Surveycited by 11
  7. 2021Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognitioncited by 9
  8. 2022Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classificationcited by 9
  9. 2021Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Imagescited by 8
  10. 2022Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparisoncited by 8
  11. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
  12. 2023GenCo: An Auxiliary Generator from Contrastive Learning for Enhanced Few-Shot Learning in Remote Sensingcited by 8
  13. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  14. 2024Dense Vision Transformer Compression with Few Samplescited by 8
  15. 2021Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classificationcited by 7
  16. 2021Fine-Grained Few Shot Learning with Foreground Object Transformationcited by 7
  17. 2021Tensor feature hallucination for few-shot learningcited by 6
  18. 2024Learning to Obstruct Few-Shot Image Classification over Restricted Classescited by 5
  19. 2021Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognitioncited by 4
  20. 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
  21. 2023Adaptive manifold for imbalanced transductive few-shot learningcited by 4
  22. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  23. 2026Spatio-temporal Decoupled Knowledge Compensator for Few-Shot Action Recognitioncited by 4
  24. 2022Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognitioncited by 3
  25. 2021Machine learning with limited datacited by 2
  26. 2025Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognitioncited by 2
  27. 2025Hyperbolic Dual Feature Augmentation for Open-Environmentcited by 2
  28. 2021Few-shot learning via tensor hallucinationcited by 1
  29. 2021Compositional Fine-Grained Low-Shot Learningcited by 1
  30. 2021Learning Class-level Prototypes for Few-shot Learningcited by 1
  31. 2022Overcoming challenges in leveraging GANs for few-shot data augmentationcited by 1
  32. 2022Disentangled Generation with Information Bottleneck for Few-Shot Learningcited by 1
  33. 2023VGTS: Visually Guided Text Spotting for Novel Categories in Historical Manuscriptscited by 1
  34. 2024Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applicationscited by 1
  35. 2025Explainable AI the Latest Advancements and New Trendscited by 1
  36. 2025Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancementcited by 1
  37. 2025Slot Attention-based Feature Filtering for Few-Shot Learningcited by 1
  38. 2022DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Deltacited by 0

50 most cited of 56 All 56 (JSON)