Computational aesthetics have seen much progress in recent years with the increasing popularity of deep learning methods. In this paper, we present two approaches that leverage on the benefits of using Global Average Pooling (GAP) to reduce the complexity of deep convolutional neural networks. The first model fine-tunes a standard CNN with a newly introduced GAP layer. The second approach extracts global and local CNN codes by reducing the dimensionality of convolution layers with individual GAP operations. We also extend these approaches to a multi-attribute network which uses a style network to regularize the aesthetic network. Experiments demonstrate the capability of attaining comparable accuracy results while reducing training complexity substantially.
poster.pdf

Paper Details
- Authors:
- Submitted On:
- 14 September 2017 - 11:17pm
- Short Link:
- Type:
- Poster
- Event:
- Presenter's Name:
- Magzhan Kairanbay
- Paper Code:
- 3435
- Document Year:
- 2017
- Cite
Keywords
Subscribe
url = {http://sigport.org/2075},
author = {Magzhan Kairanbay; John See; Lai-Kuan Wong; Yong-Lian Hii },
publisher = {IEEE SigPort},
title = {Filling the GAPs: Reducing the Complexity of Networks for Multi-attribute Image Aesthetic Prediction},
year = {2017} }
T1 - Filling the GAPs: Reducing the Complexity of Networks for Multi-attribute Image Aesthetic Prediction
AU - Magzhan Kairanbay; John See; Lai-Kuan Wong; Yong-Lian Hii
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2075
ER -