A deep architecture for unified aesthetic prediction
arXiv:1708.04890
Abstract
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.
References in corpus (13)
- Distilling the Knowledge in a Neural Network
- Explaining and Harnessing Adversarial Examples
- Intriguing properties of neural networks
- Deep Residual Learning for Image Recognition
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Going Deeper with Convolutions
- Deep Aesthetic Quality Assessment with Semantic Information
- Understanding Deep Image Representations by Inverting Them
- Deep Image Retrieval: Learning global representations for image search
- Instance-aware Semantic Segmentation via Multi-task Network Cascades
- Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
- Photo Aesthetics Ranking Network with Attributes and Content Adaptation
Cited by in corpus (5)
- Detecting Visual Design Principles in Art and Architecture through Deep Convolutional Neural Networks
- Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
- Composition-Aware Image Aesthetics Assessment
- MUSIQ: Multi-scale Image Quality Transformer
- Tumera: Tutor of Photography Beginners