Please use this identifier to cite or link to this item:
Title: Higher-order integration of hierarchical convolutional activations for fine-grained visual categorization
Authors: Cai, S 
Zuo, W
Zhang, L 
Issue Date: 2017
Publisher: Institute of Electrical and Electronics Engineers
Source: Proceedings of the IEEE International Conference on Computer Vision, 2017, 22-29 Oct. 2017, 8237325, p. 511-520 How to cite?
Abstract: The success of fine-grained visual categorization (FGVC) extremely relies on the modeling of appearance and interactions of various semantic parts. This makes FGVC very challenging because: (i) part annotation and detection require expert guidance and are very expensive (ii) parts are of different sizes and (iii) the part interactions are complex and of higher-order. To address these issues, we propose an end-to-end framework based on higherorder integration of hierarchical convolutional activations for FGVC. By treating the convolutional activations as local descriptors, hierarchical convolutional activations can serve as a representation of local parts from different scales. A polynomial kernel based predictor is proposed to capture higher-order statistics of convolutional activations for modeling part interaction. To model inter-layer part interactions, we extend polynomial predictor to integrate hierarchical activations via kernel fusion. Our work also provides a new perspective for combining convolutional activations from multiple layers. While hypercolumns simply concatenate maps from different layers, and holistically-nested network uses weighted fusion to combine side-outputs, our approach exploits higher-order intra-layer and inter-layer relations for better integration of hierarchical convolutional features. The proposed framework yields more discriminative representation and achieves competitive results on the widely used FGVC datasets.
ISBN: 9.78154E+12
DOI: 10.1109/ICCV.2017.63
Appears in Collections:Conference Paper

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Citations as of Sep 18, 2018

Google ScholarTM



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