Learning Image Aesthetics by Learning Inpainting

June Hao Ching, John See, Lai Kuan Wong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

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 languageEnglish
Title of host publication2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
PublisherIEEE
Pages2246-2250
Number of pages5
ISBN (Electronic)9781728163956
DOIs
Publication statusPublished - Oct 2020
Event2020 IEEE International Conference on Image Processing - Virtual, Abu Dhabi, United Arab Emirates
Duration: 25 Oct 202028 Oct 2020

Conference

Conference2020 IEEE International Conference on Image Processing
Abbreviated titleICIP 2020
Country/TerritoryUnited Arab Emirates
CityVirtual, Abu Dhabi
Period25/10/2028/10/20

Keywords

  • Aesthetic quality assessment
  • CNN
  • image inpainting
  • photographic rules
  • self-supervised learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Learning Image Aesthetics by Learning Inpainting'. Together they form a unique fingerprint.

Cite this