1 code implementation • 3 Jun 2024 • Guanhua Huang, Yuchen Zhang, Zhe Li, Yongjian You, Mingze Wang, Zhouwang Yang
The SCRN employs a reconstruction network to add and remove noise from text, extracting a semantic representation that is robust to local perturbations.
no code implementations • 7 Mar 2021 • Lumeng Cao, Zhouwang Yang
Specifically, we utilize the label to generate a multi-scale label affinity matrix as a structural supervision, and we use a square root kernel to compute a non-local affinity matrix on output layers.
no code implementations • 3 Feb 2021 • Yangling Ma, Zhouwang Yang
Multi-Instance Learning(MIL) aims to learn the mapping between a bag of instances and the bag-level label.
no code implementations • 8 Jan 2020 • Xishun Wang, Zhouwang Yang, Xingye Yue, Hui Wang
Subspace segmentation assumes that data comes from the union of different subspaces and the purpose of segmentation is to partition the data into the corresponding subspace.
no code implementations • 25 Sep 2019 • Hao Chen, Zhanfeng Mo, Qingyi Gao, Zhouwang Yang, Xiao Wang
To better understand the unsupervised model, GANs, we establish the generalization bound, which uniformly holds with respect to the choice of generators.
no code implementations • 25 Sep 2019 • Cheng Peng, Hao Wang, Xiao Wang, Zhouwang Yang
Generative Adversarial Networks (GANs) are powerful, but difficult to understand and train because GANs is a min-max problem.
no code implementations • 4 Sep 2018 • Yangling Ma, Yixin Luo, Zhouwang Yang
The Convolutional Neural Network (CNN) has been successfully applied in many fields during recent decades; however it lacks the ability to utilize prior domain knowledge when dealing with many realistic problems.
no code implementations • 12 Jul 2018 • Xingyu Liao, Lingxiao He, Zhouwang Yang, Chi Zhang
Video-based person re-identification (ReID) is a challenging problem, where some video tracks of people across non-overlapping cameras are available for matching.