64 citations · 91 across the 2 of their papers we have counts for
2 papers
cs.CV2022★ 27 cited
False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image
Zhaoyang Zhang, Xuying Wang, Xiaoming Mei +2
The existing SSCL of RSI is built based on constructing positive and negative sample pairs. However, due to the richness of RSI ground objects and the complexity of the RSI context…
cs.LG2022★ 64 cited
Augmentation-Free Graph Contrastive Learning of Invariant-Discriminative Representations
Haifeng Li, Jun Cao, Jiawei Zhu +3
The pretasks are mainly built on mutual information estimation, which requires data augmentation to construct positive samples with similar semantics to learn invariant signals and…