Compact Feature Representation for Image Classification Using ELMs

Dongshun Cui, Guanghao Zhang, Wei Han, Liyanaarachchi Lekamalage Chamara Kasun, Kai Hu, Guang-Bin Huang; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1015-1022

Feature representation/learning is an essential step for many computer vision tasks (like image classification) and is broadly categorized as 1) deep feature representation; 2) shallow feature representation. With the development of deep neural networks, many deep feature representation methods have been proposed and obtained many remarkable results. However, they are limited to real-world applications due to the high demand for storage space and computation ability. In our work, we focus on shallow feature representation (like PCANet) as these algorithms require less storage space and computational resources. In this paper, we have proposed a Compact Feature Representation algorithm (CFR-ELM) which consists of compact feature learning module and a post-processing module. We have tested CFR-ELM on four typical image classification databases, and the results demonstrate that our method outperforms the state-of-the-art methods.