ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation

TL;DR

This paper introduces ILGNet, a deep CNN that combines local and global features for efficient aesthetic image classification, leveraging domain adaptation with pre-trained GoogLeNet, achieving state-of-the-art results.

Contribution

ILGNet integrates Inception modules with connected local and global features, utilizing domain adaptation for improved aesthetic quality classification.

Findings

Achieves state-of-the-art accuracy on AVA database.

Faster training and testing speeds than original GoogLeNet.

Effectively combines local and global features for aesthetic assessment.

Abstract

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.