27 citations · 69 across the 4 of their papers we have counts for
4 papers
Homogeneous Tokenizer Matters: Homogeneous Visual Tokenizer for Remote Sensing Image Understanding
Run Shao, Zhaoyang Zhang, Chao Tao +3
The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. One key factor of the great comprehension power…
GraSS: Contrastive Learning with Gradient Guided Sampling Strategy for Remote Sensing Image Semantic Segmentation
Zhaoyang Zhang, Zhen Ren, Chao Tao +3
Self-supervised contrastive learning (SSCL) has achieved significant milestones in remote sensing image (RSI) understanding. Its essence lies in designing an unsupervised instance…
Generative Model Based Highly Efficient Semantic Communication Approach for Image Transmission
Tianxiao Han, Jiancheng Tang, Qianqian Yang +3
Deep learning (DL) based semantic communication methods have been explored to transmit images efficiently in recent years. In this paper, we propose a generative model based semant…
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…