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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ICIP40778.2020.9191130 | 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) |
Keywords | DocType | ISSN |
Aesthetic quality assessment, CNN, self-supervised learning, image inpainting, photographic rules | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
June Hao Ching | 1 | 0 | 0.34 |
John See | 2 | 112 | 19.55 |
Lai-Kuan Wong | 3 | 85 | 11.99 |