mlsanityData to 14 Oct 2026

ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot Learning

arXiv 2304.13287 ↗First posted 26 Apr 2023cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning (SSL) techniques have recently been integrated into the few-shot learning (FSL) framework and have shown promising results in improving the few-shot image classification performance. However, existing SSL approaches used in FSL typically seek the supervision signals from the global embedding of every single image. Therefore, during the episodic training of FSL, these methods cannot capture and fully utilize the local visual information in image samples and the data structure information of the whole episode, which are beneficial to FSL. To this end, we propose to augment the few-shot learning objective with a novel self-supervised Episodic Spatial Pretext Task (ESPT). Specifically, for each few-shot episode, we generate its corresponding transformed episode by applying a random geometric transformation to all the images in it. Based on these, our ESPT objective is defined as maximizing the local spatial relationship consistency between the original episode and the transformed one. With this definition, the ESPT-augmented FSL objective promotes learning more transferable feature representations that capture the local spatial features of different images and their inter-relational structural information in each input episode, thus enabling the model to generalize better to new categories with only a few samples. Extensive experiments indicate that our ESPT method achieves new state-of-the-art performance for few-shot image classification on three mainstay benchmark datasets. The source code will be available at: https://github.com/Whut-YiRong/ESPT.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2019A Closer Look at Few-shot Classificationcited by 684
  7. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  8. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  11. 2018Meta-learning with differentiable closed-form solverscited by 397
  12. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
23 more
  1. 2021MagFace: A Universal Representation for Face Recognition and Quality Assessmentcited by 334
  2. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  3. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  4. 2018Low-Shot Learning from Imaginary Datacited by 181
  5. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  6. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  7. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  8. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  9. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  10. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  11. 2021Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformercited by 120
  12. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  13. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  14. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  15. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  16. 2021A Broad Study on the Transferability of Visual Representations with Contrastive Learningcited by 78
  17. 2021Relational Embedding for Few-Shot Classificationcited by 74
  18. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  19. 2020Empirical Bayes Transductive Meta-Learning with Synthetic Gradientscited by 48
  20. 2020Self-supervised Knowledge Distillation for Few-shot Learningcited by 41
  21. 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
  22. 2020Spatial Contrastive Learning for Few-Shot Classificationcited by 17
  23. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 5.

6 papers.

  1. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  2. 2024KNN Transformer with Pyramid Prompts for Few-Shot Learningcited by 3
  3. 2025Revisiting Continuity of Image Tokens for Cross-domain Few-shot Learningcited by 3
  4. 2025Rethinking the Sample Relations for Few-Shot Classificationcited by 0
  5. 2025Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learningcited by 0
  6. 2025Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classificationcited by 0