Multi-Task Self-Supervised Learning for Image Segmentation Task

作     者：Gao, Lichun Khamesra, Chinmaya Kumbhar, Uday Aglawe, Ashay 

作者机构：Computer Science Department Worcester Polytechnic Institute WorcesterMA United States Robotics Department Worcester Polytechnic Institute WorcesterMA United States Data Science Department Worcester Polytechnic Institute WorcesterMA United States 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Semantic Segmentation 

摘      要：Thanks to breakthroughs in AI and Deep learning methodology, Computer vision techniques are rapidly improving. Most computer vision applications require sophisticated image segmentation to comprehend what is image and to make an analysis of each section easier. Training deep learning networks for semantic segmentation required a large amount of annotated data, which presents a major challenge in practice as it is expensive and labor-intensive to produce such data. The paper presents 1. Self-supervised techniques to boost semantic segmentation performance using multi-task learning with Depth prediction and Surface Normalization . 2. Performance evaluation of the different types of weighing techniques (UW, Nash-MTL) used for Multi-task learning. NY2D dataset was used for performance evaluation. According to our evaluation, the Nash-MTL method outperforms single task learning(Semantic Segmentation). Copyright © 2023, The Authors. All rights reserved.