Showing cs.CVShow all
2 papers · 1 filter
cs.CV2023
DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency
Yike Yuan, Xinghe Fu, Yunlong Yu +1
In this paper, we propose a simple yet effective transformer framework for self-supervised learning called DenseDINO to learn dense visual representations. To exploit the spatial i…
cs.CV2022
RBC: Rectifying the Biased Context in Continual Semantic Segmentation
Hanbin Zhao, Fengyu Yang, Xinghe Fu +1
Recent years have witnessed a great development of Convolutional Neural Networks in semantic segmentation, where all classes of training images are simultaneously available. In pra…