False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image

2 code implementations • 15 Nov 2022 • Zhaoyang Zhang, Xuying Wang, Xiaoming Mei, Chao Tao, Haifeng Li

This indicates that the SSCL model has the ability to self-differentiate FNS and that the FALSE effectively mitigates the SCI in self-supervised contrastive learning.

Contrastive Learning Segmentation +1