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

arXiv: https://arxiv.org/abs/2004.00705 · HTML: https://mlsanity.com/paper/2004.00705/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 30 of 31)

- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding](https://mlsanity.com/paper/2204.08129/) (2022)
- [Few-shot Keypoint Detection with Uncertainty Learning for Unseen Species](https://mlsanity.com/paper/2112.06183/) (2021)
- [Fine-Grained Object Classification via Self-Supervised Pose Alignment](https://mlsanity.com/paper/2203.15987/) (2022)
- [Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition](https://mlsanity.com/paper/2210.16820/) (2022)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [Evolving Interpretable Visual Classifiers with Large Language Models](https://mlsanity.com/paper/2404.09941/) (2024)
- [Compositional Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2405.17022/) (2024)
- [Disentangled Feature Representation for Few-shot Image Classification](https://mlsanity.com/paper/2109.12548/) (2021)
- [3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Na"ive](https://mlsanity.com/paper/2112.12668/) (2021)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2207.00784/) (2022)
- [Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification](https://mlsanity.com/paper/2108.13098/) (2021)
- [OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection](https://mlsanity.com/paper/2409.19899/) (2024)
- [Introspective Deep Metric Learning](https://mlsanity.com/paper/2309.09982/) (2023)
- [PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition](https://mlsanity.com/paper/2309.13822/) (2023)
- [G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models](https://mlsanity.com/paper/2506.01539/) (2025)
- [Query-Guided Networks for Few-shot Fine-grained Classification and Person Search](https://mlsanity.com/paper/2209.10250/) (2022)
- [DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery](https://mlsanity.com/paper/2502.10060/) (2025)
- [Parsing Objects at a Finer Granularity: A Survey](https://mlsanity.com/paper/2212.13693/) (2022)
- [Kernel function impact on convolutional neural networks](https://mlsanity.com/paper/2302.10266/) (2023)
- [Compositional Fine-Grained Low-Shot Learning](https://mlsanity.com/paper/2105.10438/) (2021)
- [Few-Shot Image Classification Benchmarks are Too Far From Reality: Build Back Better with Semantic Task Sampling](https://mlsanity.com/paper/2205.05155/) (2022)
- [Detail Reinforcement Diffusion Model: Augmentation Fine-Grained Visual Categorization in Few-Shot Conditions](https://mlsanity.com/paper/2309.08097/) (2023)
- [Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners](https://mlsanity.com/paper/2207.03398/) (2022)
- [Fine-grained Few-shot Recognition by Deep Object Parsing](https://mlsanity.com/paper/2207.07110/) (2022)
- [Plug-and-Play Feature Generation for Few-Shot Medical Image Classification](https://mlsanity.com/paper/2310.09471/) (2023)
- [Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classification](https://mlsanity.com/paper/2501.06909/) (2025)
- [Enhancing Environmental Robustness in Few-shot Learning via Conditional Representation Learning](https://mlsanity.com/paper/2502.01183/) (2025)

## 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