Fine-Grained Categorization by Alignments
- 1 December 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1713-1720
- https://doi.org/10.1109/iccv.2013.215
Abstract
The aim of this paper is fine-grained categorization without human interaction. Different from prior work, which relies on detectors for specific object parts, we propose to localize distinctive details by roughly aligning the objects using just the overall shape, since implicit to fine-grained categorization is the existence of a super-class shape shared among all classes. The alignments are then used to transfer part annotations from training images to test images (supervised alignment), or to blindly yet consistently segment the object in a number of regions (unsupervised alignment). We furthermore argue that in the distinction of fine grained sub-categories, classification-oriented encodings like Fisher vectors are better suited for describing localized information than popular matching oriented features like HOG. We evaluate the method on the CU-2011 Birds and Stanford Dogs fine-grained datasets, outperforming the state-of-the-art.Keywords
This publication has 17 references indexed in Scilit:
- Discriminative Color DescriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Combining randomization and discrimination for fine-grained image categorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Object Detection with Discriminatively Trained Part-Based ModelsIeee Transactions On Pattern Analysis and Machine Intelligence, 2009
- Efficient representation of local geometry for large scale object retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- Automated Flower Classification over a Large Number of ClassesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- PegasosPublished by Association for Computing Machinery (ACM) ,2007
- A Comparison of Affine Region DetectorsInternational Journal of Computer Vision, 2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- "GrabCut"ACM Transactions on Graphics, 2004
- Basic objects in natural categoriesCognitive Psychology, 1976