A deep architecture for unified aesthetic prediction
This work addresses the need for more precise aesthetic prediction in visual content curation for social media and media repositories, representing an incremental improvement over existing methods.
The paper tackled the problem of predicting aesthetic score distributions from images, which provides richer information than binary labels or mean scores, and achieved state-of-the-art results on the AVA benchmark dataset for classification, regression, and distribution prediction tasks using a single model.
Image aesthetics has become an important criterion for visual content curation on social media sites and media content repositories. Previous work on aesthetic prediction models in the computer vision community has focused on aesthetic score prediction or binary image labeling. However, raw aesthetic annotations are in the form of score histograms and provide richer and more precise information than binary labels or mean scores. Consequently, in this work we focus on the rarely-studied problem of predicting aesthetic score distributions and propose a novel architecture and training procedure for our model. Our model achieves state-of-the-art results on the standard AVA large-scale benchmark dataset for three tasks: (i) aesthetic quality classification; (ii) aesthetic score regression; and (iii) aesthetic score distribution prediction, all while using one model trained only for the distribution prediction task. We also introduce a method to modify an image such that its predicted aesthetics changes, and use this modification to gain insight into our model.