Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance

Farrell, Ryan; Oza, Om; Zhang, Ning; Morariu, Vlad I.; Darrell, Trevor; Davis, Larry S.

doi:10.1109/iccv.2011.6126238

Cited by 175 publications

(179 citation statements)

References 31 publications

Supporting

Mentioning

168

Contrasting

Order By: Relevance

“…Work on fine-grained visual categorization aims to recognize objects in a single domain, e.g., bird species [8,14]. While such problems also require making distinctions among visually close instances, our goal is to compare attributes, not categorize objects.…”

Section: Related Workmentioning

confidence: 99%

Fine-Grained Visual Comparisons with Local Learning

Grauman

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

402

302

View full text Add to dashboard Cite

Given two images, we want to predict which exhibits a particular visual attribute more than the other-even when the two images are quite similar. Existing relative attribute methods rely on global ranking functions; yet rarely will the visual cues relevant to a comparison be constant for all data, nor will humans' perception of the attribute necessarily permit a global ordering. To address these issues, we propose a local learning approach for fine-grained visual comparisons. Given a novel pair of images, we learn a local ranking model on the fly, using only analogous training comparisons. We show how to identify these analogous pairs using learned metrics. With results on three challenging datasets-including a large newly curated dataset for fine-grained comparisons-our method outperforms stateof-the-art methods for relative attribute prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

Fine-Grained Visual Comparisons with Local Learning

Grauman

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

402

302

View full text Add to dashboard Cite

show abstract

“…These images are nearly infinite in their variety, showing dogs of all shapes, sizes, and colors, under differing illumination, in innumerable poses, and in just about any location. Success in this domain will certainly lead to further success in the broader domain of automatic species identification [2][3][4][5], contributing to the ever growing area of biodiversity studies. In addition, there are some practical applications to the automatic processing of dog images.…”

Section: Introductionmentioning

confidence: 99%

Dog Breed Classification Using Part Localization

Liu

Kanazawa

Jacobs

et al. 2012

Lecture Notes in Computer Science

154

127

View full text Add to dashboard Cite

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.

show abstract

“…This challenge could be viewed as a form of fine-grained categorization, studied in other types of data e.g., for birds and faces [10,28,1,11]. Typically fine-grained categorization approaches require coarse correspondence of keypoints in order to reliably extract subtle differences in appearance.…”

Section: Related Workmentioning

confidence: 99%