RiSSNet: Contrastive Learning Network with a Relaxed Identity Sampling Strategy for Remote Sensing Image Semantic Segmentation

RiSSNet: Contrastive Learning Network with a Relaxed Identity Sampling Strategy for Remote Sensing Image Semantic Segmentation

Contrastive learning techniques make it possible to pretrain a general model in a self-supervised paradigm using a large number of unlabeled remote sensing images. The core idea is to pull positive samples defined by data augmentation techniques closer together while pushing apart randomly sampled n...

Full description

Bibliographic Details
Main Authors: Haifeng Li, Wenxuan Jing, Guo Wei, Kai Wu, Mingming Su, Lu Liu, Hao Wu, Penglong Li, Ji Qi
Format: Article
Language:English
Published: MDPI AG 2023-07-01
Series:Remote Sensing
Subjects:
semantic segmentation
remote sensing (RS)
self-supervised learning
contrastive learning
Online Access:https://www.mdpi.com/2072-4292/15/13/3427

Internet

https://www.mdpi.com/2072-4292/15/13/3427

Similar Items