Please use this identifier to cite or link to this item:
Title: Hierarchical part matching for fine-grained visual categorization
Authors: Xie, L.
Tian, Q.
Hong, R.
Yan, S. 
Zhang, B.
Keywords: Fine-Grained Visual Categorization
Foreground Inference and Segmentation
Geometric Phrase Pooling
Hierarchical Part Matching
Hierarchical Structure Learning
Issue Date: 2013
Citation: Xie, L., Tian, Q., Hong, R., Yan, S., Zhang, B. (2013). Hierarchical part matching for fine-grained visual categorization. Proceedings of the IEEE International Conference on Computer Vision : 1641-1648. ScholarBank@NUS Repository.
Abstract: As a special topic in computer vision, fine-grained visual categorization (FGVC) has been attracting growing attention these years. Different with traditional image classification tasks in which objects have large inter-class variation, the visual concepts in the fine-grained datasets, such as hundreds of bird species, often have very similar semantics. Due to the large inter-class similarity, it is very difficult to classify the objects without locating really discriminative features, therefore it becomes more important for the algorithm to make full use of the part information in order to train a robust model. In this paper, we propose a powerful flowchart named Hierarchical Part Matching (HPM) to cope with fine-grained classification tasks. We extend the Bag-of-Features (BoF) model by introducing several novel modules to integrate into image representation, including foreground inference and segmentation, Hierarchical Structure Learning (HSL), and Geometric Phrase Pooling (GPP). We verify in experiments that our algorithm achieves the state-of-the-art classification accuracy in the Caltech-UCSD-Birds-200-2011 dataset by making full use of the ground-truth part annotations. © 2013 IEEE.
Source Title: Proceedings of the IEEE International Conference on Computer Vision
ISBN: 9781479928392
DOI: 10.1109/ICCV.2013.206
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Jan 26, 2022


checked on Jan 26, 2022

Page view(s)

checked on Jan 20, 2022

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.