no code implementations • 2 Apr 2024 • Hui Xiao, Yuting Hong, Li Dong, Diqun Yan, Jiayan Zhuang, Junjie Xiong, Dongtai Liang, Chengbin Peng
Recent semi-supervised semantic segmentation approaches mainly resort to pseudo-labeling methods to exploit unlabeled data.
1 code implementation • 10 Jan 2023 • Hao Xu, Hui Xiao, Huazheng Hao, Li Dong, Xiaojie Qiu, Chengbin Peng
We also propose a mechanism to select a few pseudo-negative labels to feed into submodels.
1 code implementation • Neurocomputing 2022 • Hui Xiao, Li Dong, Kangkang Song, Hao Xu, Shuibo Fu, Diqun Yan, Chengbin Peng
In experiments, the cross-teacher module significantly improves the performance of traditional student-teacher approaches, and our framework outperforms stateof-the-art methods on benchmark datasets.
1 code implementation • Entropy 2022, 24(9), 1190; 2022 • Xu Shen, Yuyang Zhang, Yu Xie, Ka-Chun Wong, Chengbin Peng
Graph neural networks (GNNs) with feature propagation have demonstrated their power in handling unstructured data.
no code implementations • 8 Jul 2021 • Zhiyu Wang, Jiayan Zhuang, Ningyuan Xu, Sichao Ye, Jiangjian Xiao, Chengbin Peng
With the development of image recovery models, especially those based on adversarial and perceptual losses, the detailed texture portions of images are being recovered more naturally. However, these restored images are similar but not identical in detail texture to their reference images. With traditional image quality assessment methods, results with better subjective perceived quality often score lower in objective scoring. Assessment methods suffer from subjective and objective inconsistencies. This paper proposes a regional differential information entropy (RDIE) method for image quality assessment to address this problem. This approach allows better assessment of similar but not identical textural details and achieves good agreement with perceived quality. Neural networks are used to reshape the process of calculating information entropy, improving the speed and efficiency of the operation.