Multi-task convolutional neural network for image aesthetic assessment
This work addresses the challenging problem of predicting image aesthetics for AI applications, offering an incremental improvement in efficiency and performance over existing methods.
The authors tackled image aesthetic assessment by developing a multi-task convolutional neural network that jointly learns aesthetic attributes and overall scores, achieving near-human performance in Spearman's rank correlations on one benchmark and setting a new baseline on another with fewer parameters.
As people's aesthetic preferences for images are far from understood, image aesthetic assessment is a challenging artificial intelligence task. The range of factors underlying this task is almost unlimited, but we know that some aesthetic attributes affect those preferences. In this study, we present a multi-task convolutional neural network that takes into account these attributes. The proposed neural network jointly learns the attributes along with the overall aesthetic scores of images. This multi-task learning framework allows for effective generalization through the utilization of shared representations. Our experiments demonstrate that the proposed method outperforms the state-of-the-art approaches in predicting overall aesthetic scores for images in one benchmark of image aesthetics. We achieve near-human performance in terms of overall aesthetic scores when considering the Spearman's rank correlations. Moreover, our model pioneers the application of multi-tasking in another benchmark, serving as a new baseline for future research. Notably, our approach achieves this performance while using fewer parameters compared to existing multi-task neural networks in the literature, and consequently makes our method more efficient in terms of computational complexity.