Abstract
Due to the high capability of learning robust features, convolutional neural networks (CNN) are becoming a mainstay solution for many computer vision problems, including aesthetic quality assessment (AQA). However, there remains the issue that learning with CNN requires time-consuming and expensive data annotations especially for a task like AQA. In this paper, we present a novel approach to AQA that incorporates self-supervised learning (SSL) by learning how to inpaint images according to photographic rules such as rules-of-thirds and visual saliency. We conduct extensive quantitative experiments on a variety of pretext tasks and also different ways of masking patches for inpainting, reporting fairer distribution-based metrics. We also show the suitability and practicality of the inpainting task which yielded comparably good benchmark results with much lighter model complexity.
Original language | English |
---|---|
Title of host publication | 2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings |
Publisher | IEEE |
Pages | 2246-2250 |
Number of pages | 5 |
ISBN (Electronic) | 9781728163956 |
DOIs | |
Publication status | Published - Oct 2020 |
Event | 2020 IEEE International Conference on Image Processing - Virtual, Abu Dhabi, United Arab Emirates Duration: 25 Oct 2020 → 28 Oct 2020 |
Conference
Conference | 2020 IEEE International Conference on Image Processing |
---|---|
Abbreviated title | ICIP 2020 |
Country/Territory | United Arab Emirates |
City | Virtual, Abu Dhabi |
Period | 25/10/20 → 28/10/20 |
Keywords
- Aesthetic quality assessment
- CNN
- image inpainting
- photographic rules
- self-supervised learning
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition
- Signal Processing