Name
Abstract | ||
|---|---|---|
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 appearance of corresponding parts can vary dramatically, e.g., the faces of bulldogs and beagles are very different. To find accurate correspondences, we build exemplar-based geometric and appearance models of dog breeds and their face parts. Part correspondence allows us to extract and compare descriptors in like image locations. Our approach also features a hierarchy of parts (e.g., face and eyes) and breed-specific part localization. We achieve 67% recognition rate on a large real-world dataset including 133 dog breeds and 8,351 images, and experimental results show that accurate part localization significantly increases classification performance compared to state-of-the-art approaches. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-33718-5_13 | ECCV |
Keywords | Field | DocType |
dog breed classification,corresponding part,fine-grained image classification,face part,dog breed,breed-specific part localization,common part,appearance model,dog breed identification,accurate part localization,classification performance | Computer vision,Color histogram,Breed,Computer science,Artificial intelligence,Face detection,Hierarchy,Contextual image classification | Conference |
Volume | ISSN | Citations |
7572 | 0302-9743 | 60 |
PageRank | References | Authors |
2.07 | 27 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jiongxin Liu | 1 | 158 | 6.34 |
| Angjoo Kanazawa | 2 | 272 | 10.36 |
| David W. Jacobs | 3 | 4599 | 348.03 |
| Peter N. Belhumeur | 4 | 12242 | 1001.27 |