no code implementations • 8 Oct 2023 • Weihua Liu, Lin Li, Chaochao Lin, Said Boumaraf
In addition, to further heighten the amplification of forged clues, BENet incorporates a Latent-Space Attention (LSA) module.
no code implementations • 8 Oct 2023 • Weihua Liu, Youyuan Xue, Chaochao Lin, Said Boumaraf
We then fuse the dynamic disease topic labels with the original visual features of the images to highlight the abnormal regions in the original visual features to alleviate the visual data bias problem.
no code implementations • 30 Sep 2023 • Xinliang Ma, Weihua Liu, Bingying Jin
A novel approach is suggested for improving the accuracy of fault detection in distribution networks.
no code implementations • 29 Aug 2023 • Weihua Liu, Chaochao Lin
It embeds shape and margin characteristics through numerical computation and models the relationship between the thyroid nodule diagnosis results and segmentation masks.
2 code implementations • 29 Aug 2023 • Weihua Liu, Chaochao Lin, Yu Yan
In this paper, we propose an attack type robust face anti-spoofing framework under light flash, called ATR-FAS.
no code implementations • 29 Aug 2023 • Weihua Liu, Chaochao Lin, Haoping Yu, Said Boumaraf, Zhaoqiong Pi
Based on homogeneous tanh-transforms, we propose an occlusion-aware convolutional neural network for occluded face parsing.
no code implementations • 28 Jun 2023 • Weihua Liu, Yong Zuo
Our method is a general multimodal large-scale model framework, integrating diverse modalities and allowing us to tailor for specific tasks.
no code implementations • 21 Sep 2021 • Weihua Liu, Xiabi Liu
More specifically, we reconstruct the structure of the deep neural network, and optimize the new network using traditional gradient descent (GD).
no code implementations • 11 Sep 2020 • Weihua Liu, Xiabi Liua, Xiongbiao Luo, Murong Wang, Guanghui Han, Xinming Zhao, Zheng Zhu
In the first stage, the feature-extraction module is embedded into a classifier network that is trained on a large data set of GGO and non-GGO patches, which are generated by performing data augmentation from a small number of annotated CT scans.
no code implementations • 27 Jul 2020 • Weihua Liu, Xiabi Liu, Murong Wang, Ling Ma
The experiments on various classification applications, including handwritten digit recognition, lung nodule classification, face verification and face recognition, demonstrate that the proposed approach is promising to effectively deal with the problem of learning on the data with different quality and leads to the significant and stable improvements in the classification accuracy.
1 code implementation • 17 Oct 2019 • Huiyu Li, Xiabi Liu, Said Boumaraf, Weihua Liu, Xiaopeng Gong, Xiaohong Ma
The learning in the first stage is performed on the whole input to obtain an initial deep network for tumor segmenta-tion.