Title:	WSSL: WEIGHTED SELF-SUPERVISED LEARNING FRAMEWORK FOR IMAGE-INPAINTING
Author(s):	Shubham Gupta, Rahul Kunigal Ravishankar, Madhoolika Gangaraju, Poojasree Dwarkanath and Natarajan Subramanyam
ISBN:	978-989-8704-42-9
Editors:	Yingcai Xiao, Ajith Abraham, Guo Chao Peng and Jörg Roth
Year:	2022
Edition:	Single
Keywords:	Image Inpainting, Self-Supervised Learning, Weighted Pretext Task, Loss Functions, WSSL
Type:	Full Paper
First Page:	111
Last Page:	119
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	Image inpainting is the process of regenerating lost parts of the image. Supervised algorithm-based methods have shown excellent results but have two significant drawbacks. They do not perform well when tested with unseen data. They fail to capture the global context of the image, resulting in a visually unappealing result. We propose a novel self-supervised learning framework for image-inpainting: Weighted Self-Supervised Learning (WSSL) to tackle these problems. We designed WSSL to learn features from multiple weighted pretext tasks. These features are then utilized for the downstream task, image-inpainting. To improve the performance of our framework and produce more visually appealing images, we also present a novel loss function for image inpainting. The loss function takes advantage of both reconstruction loss and perceptual loss functions to regenerate the image. Our experimentation shows WSSL outperforms previous methods, and our loss function helps produce better results.
	Go Back