Dog Breed Classification Using Part Localization


We propose a novel approach to fine-grained image classification in which instances from different classes share common parts but have wide variation in shape and appearance. We use dog breed identification as a test case to show that extracting corresponding parts improves classification performance. This domain is especially challenging since the… (More)
DOI: 10.1007/978-3-642-33718-5_13



Citations per Year

99 Citations

Semantic Scholar estimates that this publication has 99 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Liu2012DogBC, title={Dog Breed Classification Using Part Localization}, author={Jiongxin Liu and Angjoo Kanazawa and David W. Jacobs and Peter N. Belhumeur}, booktitle={ECCV}, year={2012} }