Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity

Zhile Chen, Feng Li, Yuhui Quan, Yong Xu, Hui Ji; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 5231-5240

Abstract


In recent years, convolutional neural networks (CNNs) have become a prominent tool for texture recognition. The key of existing CNN-based approaches is aggregating the convolutional features into a robust yet discriminative description. This paper presents a novel feature aggregation module called CLASS (Cross-Layer Aggregation of Statistical Self-similarity) for texture recognition. We model the CNN feature maps across different layers, as a dynamic process which carries the statistical self-similarity (SSS), one well-known property of texture, from input image along the network depth dimension. The CLASS module characterizes the cross-layer SSS using a soft histogram of local differential box-counting dimensions of cross-layer features. The resulting descriptor encodes both cross-layer dynamics and local SSS of input image, providing additional discrimination over the often-used global average pooling. Integrating CLASS into a ResNet backbone, we develop CLASSNet, an effective deep model for texture recognition, which shows state-of-the-art performance in the experiments.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Chen_2021_CVPR, author = {Chen, Zhile and Li, Feng and Quan, Yuhui and Xu, Yong and Ji, Hui}, title = {Deep Texture Recognition via Exploiting Cross-Layer Statistical Self-Similarity}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {5231-5240} }