# Fine-grained Categorization -- Short Summary of our Entry for the ImageNet Challenge 2012

Source: [Fine-grained Categorization -- Short Summary of our Entry for the ImageNet Challenge 2012](<https://www.sota2.com/research/paper/68fa61151e209131ce9f2ad3>)

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

Data updated: 2025-10-25T19:52:34.486Z

Authors: Christoph G\\"oring, Alexander Freytag, Erik Rodner, Joachim Denzler

Published: 2013-10-17T16:11:53.000Z

## Abstract

In this paper, we tackle the problem of visual categorization of dog breeds, which is a surprisingly challenging task due to simultaneously present low interclass distances and high intra-class variances. Our approach combines several techniques well known in our community but often not utilized for fine-grained recognition:   (1) automatic segmentation, (2) efficient part detection, and (3) combination of multiple features. In particular, we demonstrate that a simple head detector embedded in an off-the-shelf recognition pipeline can improve recognition accuracy quite significantly, highlighting the importance of part features for fine-grained recognition tasks. Using our approach, we achieved a 24.59% mean average precision performance on the Stanford dog dataset.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1310.4759>)

[PDF](<https://arxiv.org/pdf/1310.4759.pdf>)