mlsanityData to 7 Oct 2026

Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignment

arXiv 2210.01439 ↗First posted 4 Oct 2022cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

Few-shot fine-grained recognition (FS-FGR) aims to recognize novel fine-grained categories with the help of limited available samples. Undoubtedly, this task inherits the main challenges from both few-shot learning and fine-grained recognition. First, the lack of labeled samples makes the learned model easy to overfit. Second, it also suffers from high intra-class variance and low inter-class differences in the datasets. To address this challenging task, we propose a two-stage background suppression and foreground alignment framework, which is composed of a background activation suppression (BAS) module, a foreground object alignment (FOA) module, and a local-to-local (L2L) similarity metric. Specifically, the BAS is introduced to generate a foreground mask for localization to weaken background disturbance and enhance dominative foreground objects. The FOA then reconstructs the feature map of each support sample according to its correction to the query ones, which addresses the problem of misalignment between support-query image pairs. To enable the proposed method to have the ability to capture subtle differences in confused samples, we present a novel L2L similarity metric to further measure the local similarity between a pair of aligned spatial features in the embedding space. What's more, considering that background interference brings poor robustness, we infer the pairwise similarity of feature maps using both the raw image and the refined image. Extensive experiments conducted on multiple popular fine-grained benchmarks demonstrate that our method outperforms the existing state of the art by a large margin. The source codes are available at: https://github.com/CSer-Tang-hao/BSFA-FSFG.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 40 of its 67 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

40 of 67 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2016Matching Networks for One Shot Learningcited by 2,246
  6. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  7. 2019A Closer Look at Few-shot Classificationcited by 679
  8. 2016Learning to learn by gradient descent by gradient descentcited by 616
  9. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  10. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  11. 2015Bilinear CNNs for Fine-grained Visual Recognitioncited by 228
  12. 2019Cross Attention Network for Few-shot Classificationcited by 218
28 more
  1. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  2. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  3. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  4. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  5. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  6. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  7. 2014Part-based R-CNNs for Fine-grained Category Detectioncited by 107
  8. 2015Compact Bilinear Poolingcited by 97
  9. 2018Self-Erasing Network for Integral Object Attentioncited by 95
  10. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  11. 2022Unsupervised Misaligned Infrared and Visible Image Fusion via Cross-Modality Image Generation and Registrationcited by 80
  12. 2021Relational Embedding for Few-Shot Classificationcited by 74
  13. 2018Memory Matching Networks for One-Shot Image Recognitioncited by 65
  14. 2019Associative Alignment for Few-shot Image Classificationcited by 58
  15. 2019See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classificationcited by 56
  16. 2020Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognitioncited by 50
  17. 2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
  18. 2022Image-Specific Information Suppression and Implicit Local Alignment for Text-based Person Searchcited by 38
  19. 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
  20. 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
  21. 2018Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examplescited by 27
  22. 2019PARN: Position-Aware Relation Networks for Few-Shot Learningcited by 27
  23. 2020Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classificationcited by 18
  24. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  25. 2020TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samplescited by 13
  26. 2017Fast Fine-grained Image Classification via Weakly Supervised Discriminative Localizationcited by 9
  27. 2021DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Networkcited by 9
  28. 2021Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classificationcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 4; 2025: 7; 2026: 5.

29 papers.

Sort:

By area:

  1. 2022CLIP-Driven Fine-grained Text-Image Person Re-identificationcited by 79
  2. 2023An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detectioncited by 36
  3. 2023M3Net: Multi-view Encoding, Matching, and Fusion for Few-shot Fine-grained Action Recognitioncited by 34
  4. 2023Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identificationcited by 19
  5. 2023Mutual Information-driven Triple Interaction Network for Efficient Image Dehazingcited by 18
  6. 2023RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Networkcited by 17
  7. 2023Multi-view Information Integration and Propagation for Occluded Person Re-identificationcited by 16
  8. 2023Learning Contrastive Self-Distillation for Ultra-Fine-Grained Visual Categorization Targeting Limited Samplescited by 9
  9. 2025Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learningcited by 9
  10. 2023Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identificationcited by 7
  11. 2025VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learningcited by 7
  12. 2023Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Featurescited by 6
17 more
  1. 2023Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognitioncited by 6
  2. 2024DVF: Advancing Robust and Accurate Fine-Grained Image Retrieval with Retrieval Guidelinescited by 6
  3. 2023YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidificationcited by 4
  4. 2024IFShip: Interpretable Fine-grained Ship Classification with Domain Knowledge-Enhanced Vision-Language Modelscited by 4
  5. 2026DVLA-RL: Dual-Level Vision-Language Alignment with Reinforcement Learning Gating for Few-Shot Learningcited by 2
  6. 2026Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classificationcited by 2
  7. 2024LoDisc: Learning Global-Local Discriminative Features for Self-Supervised Fine-Grained Visual Recognitioncited by 1
  8. 2026Frequency-Enhanced Dual-Subspace Networks for Few-Shot Fine-Grained Image Classificationcited by 1
  9. 2023Patch-aware Batch Normalization for Improving Cross-domain Robustnesscited by 0
  10. 2024What Happens Without Background? Constructing Foreground-Only Data for Fine-Grained Taskscited by 0
  11. 2025Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classificationcited by 0
  12. 2025Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learningcited by 0
  13. 2025Multi-scale Activation, Refinement, and Aggregation: Exploring Diverse Cues for Fine-Grained Bird Recognitioncited by 0
  14. 2025Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classificationcited by 0
  15. 2025CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspectivecited by 0
  16. 2026Expert Knowledge-Guided Decision Calibration for Accurate Fine-Grained Tree Species Classificationcited by 0
  17. 2026Uncertainty-DTW for Sequences and Visual Tokenscited by 0