no code implementations • 2 Jun 2019 • Naiyang Guan, Tongliang Liu, Yangmuzi Zhang, DaCheng Tao, Larry S. Davis
Non-negative matrix factorization (NMF) minimizes the Euclidean distance between the data matrix and its low rank approximation, and it fails when applied to corrupted data because the loss function is sensitive to outliers.
no code implementations • 11 Feb 2016 • Yangmuzi Zhang, Zhuolin Jiang, Xi Chen, Larry S. Davis
Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation.
no code implementations • 9 Feb 2016 • Xiyang Dai, Sameh Khamis, Yangmuzi Zhang, Larry S. Davis
Sparse representations have been successfully applied to signal processing, computer vision and machine learning.
no code implementations • 15 Oct 2015 • Bharat Singh, Soham De, Yangmuzi Zhang, Thomas Goldstein, Gavin Taylor
In this paper, we attempt to overcome the two above problems by proposing an optimization method for training deep neural networks which uses learning rates which are both specific to each layer in the network and adaptive to the curvature of the function, increasing the learning rate at low curvature points.
no code implementations • 19 Aug 2014 • Yangmuzi Zhang, Diane Larlus, Florent Perronnin
A natural approach to teaching a visual concept, e. g. a bird species, is to show relevant images.
no code implementations • CVPR 2013 • Yangmuzi Zhang, Zhuolin Jiang, Larry S. Davis
An approach to learn a structured low-rank representation for image classification is presented.