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

Source: [Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition](<https://www.sota2.com/research/paper/68fa67561e209131cea159f6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:01:46.445Z

Authors: Luming Tang, Davis Wertheimer, Bharath Hariharan

Published: 2020-04-01T21:00:06.000Z

## Abstract

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

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Fine-grained Visual Recognition on CUB (test)](<https://www.sota2.com/research/sota/fine-grained-visual-recognition-on-cub-test.md>): Fine-grained Visual Recognition; CUB (test); All-Shot Accuracy: 63.51.

- [Fine-grained visual classification on NABirds (test)](<https://www.sota2.com/research/sota/fine-grained-visual-classification-on-nabirds-test.md>): Fine-grained visual classification; NABirds (test); Top-1 Accuracy: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2004.00705>)

[PDF](<https://arxiv.org/pdf/2004.00705.pdf>)
