2 papers
cs.LG2019
Deep Learning for 2D and 3D Rotatable Data: An Overview of Methods
Luca Della Libera, Vladimir Golkov, Yue Zhu +2
Convolutional networks are successful due to their equivariance/invariance under translations. However, rotatable data such as images, volumes, shapes, or point clouds require proc…
cs.LG2017
Multi-Label Learning with Global and Local Label Correlation
Yue Zhu, James T. Kwok, Zhi-Hua Zhou
It is well-known that exploiting label correlations is important to multi-label learning. Existing approaches either assume that the label correlations are global and shared by all…