DocumentCode :
1688692
Title :
Positive and negative max pooling for image classification
Author :
Bin Wang ; Yu Liu ; WenHua Xiao ; Zhihui Xiong ; Maojun Zhang
Author_Institution :
Coll. of Inf. Syst. & Manage., Nat. Univ. of Defense Technol., Changsha, China
fYear :
2013
Firstpage :
278
Lastpage :
279
Abstract :
Max pooling has been regard as the best pooling method in image classification when image features are coded by sparse coding [2]. However, max pooling reduces the classification discrimination, since it doesn´t distinguish the sign of coding coefficient but only selects the max absolute value. In order to increase the image representation discrimination, we preserve the sign of code coefficient and develop a feature pooling method named PN-Max pooling. Experimental results show that PN-Max pooling achieves higher image classification accuracy than Max pooling.
Keywords :
feature extraction; image classification; image coding; image representation; PN-max pooling; classification discrimination; coding coefficient; feature pooling method; image classification; image feature coding; image representation discrimination; max absolute value; negative max pooling; positive max pooling; sparse coding; Accuracy; Encoding; Feature extraction; Image classification; Image coding; Image recognition; Visualization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Consumer Electronics (ICCE), 2013 IEEE International Conference on
Conference_Location :
Las Vegas, NV
ISSN :
2158-3994
Print_ISBN :
978-1-4673-1361-2
Type :
conf
DOI :
10.1109/ICCE.2013.6486894
Filename :
6486894
Link To Document :
بازگشت