Journal
PATTERN RECOGNITION
Volume 91, Issue -, Pages 34-46Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.patcog.2019.02.003
Keywords
Deep convolutional feature; Sparse coding; Locality-aware; Texture classification
Funding
- Natural Science Foundation of China (NSFC) [61702037, 61773062]
- Beijing Municipal Natural Science Foundation [L172027]
- Beijing Institute of Technology Research Fund Program for Young Scholars
Ask authors/readers for more resources
Recent studies have demonstrated advantages of the representations learned by Convolutional Neural Networks (CNNs) in providing an appealing paradigm for visual classification tasks. Most existing methods adopt activations from the last fully connected layer as the image representation. This paper advocates exploiting appropriately convolutional layer activations to constitute a powerful descriptor for texture classification under an end-to-end learning framework. The main component of our method is a new locality-aware coding layer conducted with the locality constraint, where the dictionary and the encoding representation are learned simultaneously. The layer is readily amenable to training via the backpropagation as the locality-aware coding process has an analytical solution. It is capable of capturing class-specific information which makes the learned convolutional features more robust. The resulting representation is particularly useful for texture classification. Comprehensive experiments on the DTD, FMD and KTH-T2b datasets show that our approach notably outperforms the state-of-the-art methods. (C) 2019 Published by Elsevier Ltd.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available