mlsanityData to 14 Oct 2026

CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective

arXiv 2512.21617 ↗First posted 25 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Few-shot fine-grained visual categorization (FS-FGVC) focuses on identifying various subcategories within a common superclass given just one or few support examples. Most existing methods aim to boost classification accuracy by enriching the extracted features with discriminative part-level details. However, they often overlook the fact that the set of support samples acts as a confounding variable, which hampers the FS-FGVC performance by introducing biased data distribution and misguiding the extraction of discriminative features. To address this issue, we propose a new causal FS-FGVC (CausalFSFG) approach inspired by causal inference for addressing biased data distributions through causal intervention. Specifically, based on the structural causal model (SCM), we argue that FS-FGVC infers the subcategories (i.e., effect) from the inputs (i.e., cause), whereas both the few-shot condition disturbance and the inherent fine-grained nature (i.e., large intra-class variance and small inter-class variance) lead to unobservable variables that bring spurious correlations, compromising the final classification performance. To further eliminate the spurious correlations, our CausalFSFG approach incorporates two key components: (1) Interventional multi-scale encoder (IMSE) conducts sample-level interventions, (2) Interventional masked feature reconstruction (IMFR) conducts feature-level interventions, which together reveal real causalities from inputs to subcategories. Extensive experiments and thorough analyses on the widely-used public datasets, including CUB-200-2011, Stanford Dogs, and Stanford Cars, demonstrate that our CausalFSFG achieves new state-of-the-art performance. The code is available at https://github.com/PKU-ICST-MIPL/CausalFSFG_TMM.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 36 of its 72 references that are in the map. First posted on arXiv 25 Dec 2025.

Builds on

36 of 72 references.

References · 36

  1. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  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. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  7. 2018How to train your MAMLcited by 309
  8. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  9. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  10. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  11. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  12. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
24 more
  1. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  2. 2017Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributionscited by 126
  3. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  4. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  5. 2020Interventional Few-Shot Learningcited by 112
  6. 2020Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patchescited by 92
  7. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
  8. 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
  9. 2014Visual Causal Feature Learningcited by 59
  10. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  11. 2017Object-Part Attention Model for Fine-grained Image Classificationcited by 54
  12. 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
  13. 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
  14. 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
  15. 2019PARN: Position-Aware Relation Networks for Few-Shot Learningcited by 27
  16. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  17. 2022SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorizationcited by 19
  18. 2020Attributes-Guided and Pure-Visual Attention Alignment for Few-Shot Recognitioncited by 15
  19. 2022Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classificationcited by 12
  20. 2017Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localizationcited by 9
  21. 2021Fine-Grained Few Shot Learning with Foreground Object Transformationcited by 7
  22. 2023Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognitioncited by 6
  23. 2022Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulationcited by 4
  24. 2025Transfer Learning and Mixup for Fine-Grained Few-Shot Fungi Classificationcited by 1

Built on by

Not cited yet.