Talk · Proceedings - International Conference on Image Processing · September 1, 2017
Filling the gaps: Reducing the complexity of networks for multi-attribute image aesthetic prediction
Magzhan Kairanbay, John See, Lai-Kuan Wong, Yong-Lian Hii
Abstract
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.
More by Magzhan Kairanbay
- End-to-End VITS Outperforms Two-Stage Tacotron 2 Synthesis for Kazakh: A Comparative Study on a New Multi-Domain Speech CorpusAlgorithms · 2026
- Vision-Language Temporal Analysis for Illegal Waste Dumping Detection in Surveillance VideosIEEE/CVF Winter Conference on Applications of Computer Vision Workshops · 2026 · Citations: 2
- Real-Time Multi-Parameter Petroleum Coke Quality Monitoring Using Computer Vision and Integrated Anomaly Detection for Aluminum Smelting OperationsInternational Conference on Computer and Applications · 2025
- Multi-Dimensional Tail Classification in Procurement Spend Analysis: A Data-Driven Approach to Strategic Sourcing OptimizationInternational Conference on Computer and Applications · 2025