Locally-Transferred Fisher Vectors for Texture Classification

Yang Song, Fan Zhang, Qing Li, Heng Huang, Lauren J. O'Donnell, Weidong Cai; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4912-4920


Texture classification has been extensively studied in computer vision. Recent research shows that the combination of Fisher vector (FV) encoding and convolutional neural network (CNN) provides significant improvement in texture classification over the previous feature representation methods. However, by truncating the CNN model at the last convolutional layer, the CNN-based FV descriptors would not incorporate the full capability of neural networks in feature learning. In this study, we propose that we can further transform the CNN-based FV descriptors in a neural network model to obtain more discriminative feature representations. In particular, we design a locally-transferred Fisher vector (LFV) method, which involves a multi-layer neural network model containing locally connected layers to transform the input FV descriptors with filters of locally shared weights. The network is optimized based on the hinge loss of classification, and transferred FV descriptors are then used for image classification. Our results on three challenging texture image datasets show improved performance over the state of the art.

Related Material

author = {Song, Yang and Zhang, Fan and Li, Qing and Huang, Heng and O'Donnell, Lauren J. and Cai, Weidong},
title = {Locally-Transferred Fisher Vectors for Texture Classification},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}