ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation
This addresses aesthetic quality classification for image analysis, but it is incremental as it builds on GoogLeNet with domain adaptation.
The paper tackles aesthetic image classification by labeling images as high or low quality, proposing ILGNet, a deep CNN that combines Inception modules with connected local and global features, achieving state-of-the-art results on the AVA database with faster training and testing speeds than GoogLeNet.
In this paper, we 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 an 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 our connected layers on an large scale database of aesthetic related images: AVA, i.e. \emph{domain adaptation}. The experiments reveal that our model achieves the state of the arts in AVA database. Both the training and testing speeds of our model are higher than those of the original GoogLeNet.