mlsanityData to 7 Oct 2026

Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification

arXiv 2211.17161 ↗First posted 30 Nov 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

The main challenge for fine-grained few-shot image classification is to learn feature representations with higher inter-class and lower intra-class variations, with a mere few labelled samples. Conventional few-shot learning methods however cannot be naively adopted for this fine-grained setting -- a quick pilot study reveals that they in fact push for the opposite (i.e., lower inter-class variations and higher intra-class variations). To alleviate this problem, prior works predominately use a support set to reconstruct the query image and then utilize metric learning to determine its category. Upon careful inspection, we further reveal that such unidirectional reconstruction methods only help to increase inter-class variations and are not effective in tackling intra-class variations. In this paper, we for the first time introduce a bi-reconstruction mechanism that can simultaneously accommodate for inter-class and intra-class variations. In addition to using the support set to reconstruct the query set for increasing inter-class variations, we further use the query set to reconstruct the support set for reducing intra-class variations. This design effectively helps the model to explore more subtle and discriminative features which is key for the fine-grained problem in hand. Furthermore, we also construct a self-reconstruction module to work alongside the bi-directional module to make the features even more discriminative. Experimental results on three widely used fine-grained image classification datasets consistently show considerable improvements compared with other methods. Codes are available at: https://github.com/PRIS-CV/Bi-FRN.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 28 of its 37 references that are in the map. First posted on arXiv 30 Nov 2022.

Builds on

28 of 37 references.

References · 28

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  10. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  11. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  12. 2017Few-Shot Learning with Graph Neural Networkscited by 324
16 more
  1. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  2. 2021Escaping the Big Data Paradigm with Compact Transformerscited by 261
  3. 2020Eigen-CAM: Class Activation Map using Principal Componentscited by 188
  4. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  5. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  6. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  7. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  8. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  9. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  10. 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
  11. 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
  12. 2021Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developmentscited by 23
  13. 2021How to Train Your MAML to Excel in Few-Shot Classificationcited by 22
  14. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  15. 2021NDPNet: A novel non-linear data projection network for few-shot fine-grained image classificationcited by 13
  16. 2019Few-shot Learning for Domain-specific Fine-grained Image Classificationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 6; 2026: 1.

12 papers.

  1. 2023EWT: Efficient Wavelet-Transformer for Single Image Denoisingcited by 11
  2. 2024Towards Generative Class Prompt Learning for Fine-grained Visual Recognitioncited by 2
  3. 2026Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classificationcited by 1
  4. 2023Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Workcited by 0
  5. 2024Hybrid Feature Collaborative Reconstruction Network for Few-Shot Fine-Grained Image Classificationcited by 0
  6. 2024Video-to-Task Learning via Motion-Guided Attention for Few-Shot Action Recognitioncited by 0
  7. 2025Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classificationcited by 0
  8. 2025Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classificationcited by 0
  9. 2025Shallow Deep Learning Can Still Excel in Fine-Grained Few-Shot Learningcited by 0
  10. 2025MetaLab: Few-Shot Game Changer for Image Recognitioncited by 0
  11. 2025Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classificationcited by 0
  12. 2025CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspectivecited by 0