# Part-based R-CNNs for Fine-grained Category Detection

Source: [Part-based R-CNNs for Fine-grained Category Detection](<https://www.sota2.com/research/paper/68fa61671e209131ce9f41ce>)

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

Data updated: 2026-01-04T02:48:11.068Z

Authors: Ning Zhang, Jeff Donahue, Ross Girshick, Trevor Darrell

Published: 2014-07-15T02:32:16.000Z

## Abstract

Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts. Methods for pose-normalized representations have been proposed, but generally presume bounding box annotations at test time due to the difficulty of object detection. We propose a model for fine-grained categorization that overcomes these limitations by leveraging deep convolutional features computed on bottom-up region proposals. Our method learns whole-object and part detectors, enforces learned geometric constraints between them, and predicts a fine-grained category from a pose-normalized representation. Experiments on the Caltech-UCSD bird dataset confirm that our method outperforms state-of-the-art fine-grained categorization methods in an end-to-end evaluation without requiring a bounding box at test time.

## 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.

- [Period Dating on Bronze Ding (test)](<https://www.sota2.com/research/sota/period-dating-on-bronze-ding-test.md>): Period Dating; Bronze Ding (test); Overall Accuracy (OA): 69.45.

- [Image Classification on CUB-200-2011 (test)](<https://www.sota2.com/research/sota/image-classification-on-cub-200-2011-test.md>): Image Classification; CUB-200-2011 (test); Top-1 Acc: 76.4.

- [Fine-grained Image Classification on CUB-200 2011](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub-200-2011.md>): Fine-grained Image Classification; CUB-200 2011; Accuracy: 73.9.

- [Fine-grained Image Classification on CUB200 2011 (test)](<https://www.sota2.com/research/sota/fine-grained-image-classification-on-cub200-2011-test.md>): Fine-grained Image Classification; CUB200 2011 (test); Accuracy: 81.6.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1407.3867>)

[PDF](<https://arxiv.org/pdf/1407.3867.pdf>)

[Implementation](<http://www.eecs.berkeley.edu/~lbourdev/poselets>)