mlsanityData to 7 Oct 2026

Delta-encoder: an effective sample synthesis method for few-shot object recognition

arXiv 1806.04734 ↗First posted 12 Jun 2018cs.CVcited by 89

Not on the map. Why?

Abstract (arXiv)

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we proposes a simple yet effective method for few-shot (and one-shot) object recognition. Our approach is based on a modified auto-encoder, denoted Delta-encoder, that learns to synthesize new samples for an unseen category just by seeing few examples from it. The synthesized samples are then used to train a classifier. The proposed approach learns to both extract transferable intra-class deformations, or "deltas", between same-class pairs of training examples, and to apply those deltas to the few provided examples of a novel class (unseen during training) in order to efficiently synthesize samples from that new class. The proposed method improves over the state-of-the-art in one-shot object-recognition and compares favorably in the few-shot case. Upon acceptance code will be made available.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 28; 2023: 18; 2024: 11; 2025: 5; 2026: 4.

89 papers.

Sort:

By area:

  1. 2021A Survey of Data Augmentation Approaches for NLPcited by 408
  2. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  3. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  4. 2021A Survey on Data Augmentation for Text Classificationcited by 111
  5. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
  6. 2021RSG: A Simple but Effective Module for Learning Imbalanced Datasetscited by 61
  7. 2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
  8. 2021Hallucination Improves Few-Shot Object Detectioncited by 50
  9. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  10. 2022Spectral Feature Augmentation for Graph Contrastive Learning and Beyondcited by 49
  11. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  12. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
38 more
  1. 2023M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognitioncited by 34
  2. 2022Matching Feature Sets for Few-Shot Image Classificationcited by 25
  3. 2022Self-Supervision Can Be a Good Few-Shot Learnercited by 19
  4. 2022Towards better understanding and better generalization of few-shot classification in histology images with contrastive learningcited by 16
  5. 2023Hallucination Improves the Performance of Unsupervised Visual Representation Learningcited by 16
  6. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  7. 2022Enabling hand gesture customization on wrist-worn devicescited by 15
  8. 2022Adaptive Distribution Calibration for Few-Shot Learning with Hierarchical Optimal Transportcited by 14
  9. 2022Masked Autoencoders are Robust Data Augmentorscited by 13
  10. 2021Disentangled Feature Representation for Few-shot Image Classificationcited by 12
  11. 2022Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometrycited by 12
  12. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  13. 2023AGI for Agriculturecited by 9
  14. 2021ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classificationcited by 8
  15. 2021Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Imagescited by 8
  16. 2023GeNIe: Generative Hard Negative Images Through Diffusioncited by 8
  17. 2024Dense Vision Transformer Compression with Few Samplescited by 8
  18. 2021Fine-Grained Few Shot Learning with Foreground Object Transformationcited by 7
  19. 2022PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learnerscited by 7
  20. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
  21. 2023Instance-Conditioned GAN Data Augmentation for Representation Learningcited by 7
  22. 2023Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognitioncited by 7
  23. 2021Tensor feature hallucination for few-shot learningcited by 6
  24. 2021MetaCloth: Learning Unseen Tasks of Dense Fashion Landmark Detection from a Few Samplescited by 6
  25. 2023ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learningcited by 6
  26. 2021Good-Enough Example Extrapolationcited by 5
  27. 2022Few-Shot Non-Parametric Learning with Deep Latent Variable Modelcited by 5
  28. 2022AugCSE: Contrastive Sentence Embedding with Diverse Augmentationscited by 5
  29. 2024Learning to Obstruct Few-Shot Image Classification over Restricted Classescited by 5
  30. 2021Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognitioncited by 4
  31. 2021Dizygotic Conditional Variational AutoEncoder for Multi-Modal and Partial Modality Absent Few-Shot Learningcited by 4
  32. 2021Exploring Category-correlated Feature for Few-shot Image Classificationcited by 4
  33. 2022PatchMix Augmentation to Identify Causal Features in Few-shot Learningcited by 4
  34. 2023Adaptive Parametric Prototype Learning for Cross-Domain Few-Shot Classificationcited by 4
  35. 2024Enhanced Few-Shot Class-Incremental Learning via Ensemble Modelscited by 4
  36. 2021Multi-Agent Semi-Siamese Training for Long-tail and Shallow Face Learningcited by 3
  37. 2022Few-shot Learning as Cluster-induced Voronoi Diagrams: A Geometric Approachcited by 3
  38. 2022Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognitioncited by 3

50 most cited of 89 All 89 (JSON)