mlsanityData to 7 Oct 2026

Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition

arXiv 2004.00705 ↗First posted 1 Apr 2020cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e.g., birds) based on a few images alone. This requires a remarkable degree of invariance to pose, articulation and background. A solution is to use pose-normalized representations: first localize semantic parts in each image, and then describe images by characterizing the appearance of each part. While such representations are out of favor for fully supervised classification, we show that they are extremely effective for few-shot fine-grained classification. With a minimal increase in model capacity, pose normalization improves accuracy between 10 and 20 percentage points for shallow and deep architectures, generalizes better to new domains, and is effective for multiple few-shot algorithms and network backbones. Code is available at https://github.com/Tsingularity/PoseNorm_Fewshot

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 10; 2023: 6; 2024: 4; 2025: 4.

30 papers.

Sort:

By area:

  1. 2023Emergent Correspondence from Image Diffusioncited by 437
  2. 2021Fine-Grained Image Analysis with Deep Learning: A Surveycited by 135
  3. 2022Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understandingcited by 102
  4. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  5. 2022Fine-Grained Object Classification via Self-Supervised Pose Alignmentcited by 22
  6. 2022Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognitioncited by 22
  7. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  8. 2024Evolving Interpretable Visual Classifiers with Large Language Modelscited by 18
  9. 2024Compositional Few-Shot Class-Incremental Learningcited by 18
  10. 2021Disentangled Feature Representation for Few-shot Image Classificationcited by 12
  11. 20213D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ivecited by 10
  12. 2024Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignmentcited by 10
18 more
  1. 2022Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classificationcited by 9
  2. 2021Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classificationcited by 8
  3. 2024OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detectioncited by 8
  4. 2023Introspective Deep Metric Learningcited by 7
  5. 2023PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognitioncited by 5
  6. 2025G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Modelscited by 5
  7. 2022Query-Guided Networks for Few-shot Fine-grained Classification and Person Searchcited by 3
  8. 2025DiSciPLE: Learning Interpretable Programs for Scientific Visual Discoverycited by 3
  9. 2022Parsing Objects at a Finer Granularity: A Surveycited by 2
  10. 2023Kernel function impact on convolutional neural networkscited by 2
  11. 2021Compositional Fine-Grained Low-Shot Learningcited by 1
  12. 2022Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Samplingcited by 1
  13. 2023Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditionscited by 1
  14. 2022Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learnerscited by 0
  15. 2022Fine-grained Few-shot Recognition by Deep Object Parsingcited by 0
  16. 2023Plug-and-Play Feature Generation for Few-Shot Medical Image Classificationcited by 0
  17. 2025Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classificationcited by 0
  18. 2025Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learningcited by 0