mlsanityData to 14 Oct 2026

LSFSL: Leveraging Shape Information in Few-shot Learning

arXiv 2304.06672 ↗First posted 13 Apr 2023cs.CV cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks, such as shortcut learning and texture bias behaviors, are further exacerbated. Moreover, the significance of addressing shortcut learning is not yet fully explored in the few-shot setup. To address these issues, we propose LSFSL, which enforces the model to learn more generalizable features utilizing the implicit prior information present in the data. Through comprehensive analyses, we demonstrate that LSFSL-trained models are less vulnerable to alteration in color schemes, statistical correlations, and adversarial perturbations leveraging the global semantics in the data. Our findings highlight the potential of incorporating relevant priors in few-shot approaches to increase robustness and generalization.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 38 of its 55 references that are in the map. First posted on arXiv 13 Apr 2023.

Builds on

38 of 55 references.

References · 38

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  5. 2020Shortcut Learning in Deep Neural Networkscited by 1,969
  6. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  7. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  9. 2018Born Again Neural Networkscited by 546
  10. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  11. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  12. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
26 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  3. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  4. 2018Meta-learning with differentiable closed-form solverscited by 397
  5. 2019A Baseline for Few-Shot Image Classificationcited by 298
  6. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  7. 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
  8. 2019Deep Semantic Segmentation of Natural and Medical Images: A Reviewcited by 125
  9. 2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 118
  10. 2017Measuring the tendency of CNNs to Learn Surface Statistical Regularitiescited by 87
  11. 2020Learning to Continually Learncited by 84
  12. 2020Meta-Learning with Adaptive Hyperparameterscited by 79
  13. 2019Transductive Episodic-Wise Adaptive Metric for Few-Shot Learningcited by 67
  14. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  15. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  16. 2020On the Texture Bias for Few-Shot CNN Segmentationcited by 38
  17. 2020Biologically Inspired Mechanisms for Adversarial Robustnesscited by 29
  18. 2022On the link between conscious function and general intelligence in humans and machinescited by 16
  19. 2021A Closer Look at Prototype Classifier for Few-shot Image Classificationcited by 15
  20. 2021Combining Diverse Feature Priorscited by 12
  21. 2022A Comprehensive Study of Real-Time Object Detection Networks Across Multiple Domains: A Surveycited by 12
  22. 2022Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Samplingcited by 8
  23. 2022InBiaseD: Inductive Bias Distillation to Improve Generalization and Robustness through Shape-awarenesscited by 5
  24. 2019Texture Bias Of CNNs Limits Few-Shot Classification Performancecited by 3
  25. 2022A Simple Approach to Adversarial Robustness in Few-shot Image Classificationcited by 3
  26. 2019Improving the robustness of ImageNet classifiers using elements of human visual cognitioncited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learningcited by 11
  2. 2024Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanismscited by 4
  3. 2023Low-shot Object Learning with Mutual Exclusivity Biascited by 2
  4. 2025MEBench: A Novel Benchmark for Understanding Mutual Exclusivity Bias in Vision-Language Modelscited by 1