Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence

Abstract

Aesthetic quality prediction is a challenging task in the computer vision community because of the complex interplay with semantic contents and photographic technologies. Recent studies on the powerful deep learning based aesthetic quality assessment usually use a binary high-low label or a numerical score to represent the aesthetic quality. However the scalar representation cannot describe well the underlying varieties of the human perception of aesthetics. In this work, we propose to predict the aesthetic score distribution (i.e., a score distribution vector of the ordinal basic human ratings) using Deep Convolutional Neural Network (DCNN). Conventional DCNNs which aim to minimize the difference between the predicted scalar numbers or vectors and the ground truth cannot be directly used for the ordinal basic rating distribution. Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization). Experimental results on large scale aesthetic dataset demonstrate the effectiveness of our introduced CJS-CNN in this task.

Aesthetic Assessment of Packaging Design Based on Con-Transformer

“…Deep learning based aesthetic assessment methods introduce deep neural network into the task of image aesthetic assessment, and the assessment results are generally better than the traditional methods. For instance, by modifying the convolutional neural network, researchers , Jin 2017) can make it suitable for solving different image aesthetic assessment problems. Jin et al (Jin 2017) proposed the deep convolution neural network RS-CJS.…”

Atmospheric Boundary Layer Wind Profile Estimation Using Neural Networks, Mesoscale Models, and LiDAR Measurements

“…The closer is to 0, the more similar the two distribution functions. As this function is not symmetric, usually it is preferable to use the Jensen–Shannon divergence [ 42 ], given by: in which . Probability density function (PDF) estimation is important for several applications of interest, such as wind energy, risk management, climate studies, air pollution dispersion studies, etc.…”

Another scale-guided parallel transformer for image aesthetic assessment

“…14, a binary classification task is questionable for IAA because of the individual diversity in aesthetics. Considering this, many methods 15 – 17 are proposed to predict score distribution, which takes into account statistical characteristics of individual aesthetics by utilizing the distribution of the individual ratings. The aforementioned methods achieve more accurate aesthetics but ignore aesthetic-related attributes.…”