ILGNet: inception modules with connected local and global features for efficient image aesthetic quality classification using domain adaptation. Issue 2 (19th July 2018)

• Record Type: Journal Article
• Authors: Jin, Xin; Wu, Le; Li, Xiaodong; Zhang, Xiaokun; Chi, Jingying; Peng, Siwei; Ge, Shiming; Zhao, Geng; Li, Shuying
• Is Part Of: IET computer vision. Volume 13:Issue 2(2019)
• Page Start: 206
• Page End: 212
• Publication Date: 2018-07-19
• Subjects: image classification -- feature extraction -- feedforward neural nets -- visual databases; ILGNet -- inception modules -- connected local features -- connected global features -- efficient image aesthetic quality classification -- domain adaptation -- high-aesthetic quality -- low-aesthetic quality -- deep convolutional neural network -- GoogLeNet -- large-scale image classification problem -- large-scale aesthetic-related image database -- AVA database; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2018.5249
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : In this study, the authors address a challenging problem of aesthetic image classification, which is to label an input image as high‐ or low‐aesthetic quality. We take both the local and global features of images into consideration. A novel deep convolutional neural network named ILGNet is proposed, which combines both the inception modules and a connected layer of both local and global features. The ILGnet is based on GoogLeNet. Thus, it is easy to use a pre‐trained GoogLeNet for large‐scale image classification problem and fine tune their connected layers on a large‐scale database of aesthetic‐related images: AVA, i.e. domain adaptation . The experiments reveal that their model achieves the state of the arts in AVA database. Both the training and testing speeds of their model are higher than those of the original GoogLeNet.