Learning Convolutional Nonlinear Features for K Nearest Neighbor Image Classification

Weiqiang Ren, Yinan Yu, Junge Zhang, Kaiqi Huang
2014 2014 22nd International Conference on Pattern Recognition  
Learning low-dimensional feature representations is a crucial task in machine learning and computer vision. Recently the impressive breakthrough in general object recognition made by large scale convolutional networks shows that convolutional networks are able to extract discriminative hierarchical features in large scale object classification task. However, for vision tasks other than end-to-end classification, such as K Nearest Neighbor classification, the learned intermediate features are
more » ... necessary optimal for the specific problem. In this paper, we aim to exploit the power of deep convolutional networks and optimize the output feature layer with respect to the task of K Nearest Neighbor (kNN) classification. By directly optimizing the kNN classification error on training data, we in fact learn convolutional nonlinear features in a data-driven and task-driven way. Experimental results on standard image classificatioin benchmarks show that the proposed method is able to learn better feature representations than other general end-to-end classification methods on kNN classification task.
doi:10.1109/icpr.2014.746 dblp:conf/icpr/RenYZH14 fatcat:7ozsr5o6jjeype4xq2gmo3btoq