Interactive: Inter-layer activeness propagation

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
2016, pp. 270 - 279
Issue Date:
2016-12-12
Full metadata record
Files in This Item:
Filename Description Size
07780405.pdfPublished version1.7 MB
Adobe PDF
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 highlevel context and improving the descriptive power of lowlevel 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.
Please use this identifier to cite or link to this item: