An increasing number of computer vision tasks can be tackled with deep features, which are the intermediate outputs of a pre-trained Convolutional Neural Network. Despite the astonishing performance, deep features extracted from low-level neurons are still below satisfaction, arguably because they cannot access the spatial context contained in the higher layers. In this paper, we present InterActive, a novel algorithm which computes the activeness of neurons and network connections. Activeness is propagated through a neural network in a top-down manner, carrying high-level context and improving the descriptive power of low-level and mid-level neurons. Visualization indicates that neuron activeness can be interpreted as spatial-weighted neuron responses. We achieve state-of-the-art classification performance on a wide range of image datasets.
@article{arxiv.1605.00052,
title = {InterActive: Inter-Layer Activeness Propagation},
author = {Lingxi Xie and Liang Zheng and Jingdong Wang and Alan Yuille and Qi Tian},
journal= {arXiv preprint arXiv:1605.00052},
year = {2016}
}