mlsanityData to 14 Oct 2026

MetaLab: Few-Shot Game Changer for Image Recognition

arXiv 2507.22057 ↗First posted 29 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Difficult few-shot image recognition has significant application prospects, yet remaining the substantial technical gaps with the conventional large-scale image recognition. In this paper, we have proposed an efficient original method for few-shot image recognition, called CIELab-Guided Coherent Meta-Learning (MetaLab). Structurally, our MetaLab comprises two collaborative neural networks: LabNet, which can perform domain transformation for the CIELab color space and extract rich grouped features, and coherent LabGNN, which can facilitate mutual learning between lightness graph and color graph. For sufficient certification, we have implemented extensive comparative studies on four coarse-grained benchmarks, four fine-grained benchmarks, and four cross-domain few-shot benchmarks. Specifically, our method can achieve high accuracy, robust performance, and effective generalization capability with one-shot sample per class. Overall, all experiments have demonstrated that our MetaLab can approach 99% uparrowdownarrow accuracy, reaching the human recognition ceiling with little visual deviation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 41 of its 63 references that are in the map. First posted on arXiv 29 Jul 2025.

Builds on

41 of 63 references.

References · 41

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  6. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  7. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  8. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  9. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  10. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  11. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  12. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
29 more
  1. 2016Using Deep Learning for Image-Based Plant Disease Detectioncited by 219
  2. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  3. 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 185
  4. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  5. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  6. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  7. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  8. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  9. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  10. 2021Large Scale Visual Food Recognitioncited by 75
  11. 2021Relational Embedding for Few-Shot Classificationcited by 74
  12. 2023StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learningcited by 53
  13. 2022Generating Representative Samples for Few-Shot Classificationcited by 39
  14. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  15. 2022Adversarial Feature Augmentation for Cross-domain Few-shot Classificationcited by 36
  16. 2019Few-Shot Learning with Localization in Realistic Settingscited by 34
  17. 2023Semantic Prompt for Few-Shot Image Recognitioncited by 29
  18. 2020Variational Feature Disentangling for Fine-Grained Few-Shot Classificationcited by 26
  19. 2024Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learningcited by 26
  20. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  21. 2022Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learningcited by 23
  22. 2022Self-Promoted Supervision for Few-Shot Transformercited by 22
  23. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  24. 2023Context-Aware Meta-Learningcited by 21
  25. 2021Learning to Affiliate: Mutual Centralized Learning for Few-shot Classificationcited by 18
  26. 2023Simple Semantic-Aided Few-Shot Learningcited by 15
  27. 2021Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learningcited by 12
  28. 2022Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classificationcited by 12
  29. 2017Deep Mixture of Diverse Experts for Large-Scale Visual Recognitioncited by 1

Built on by

Not cited yet.