Jianren Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jianren Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Cindy Le
Columbia University Carnegie Mellon University Carnegie Mellon University University of Michigan Carnegie Mellon University
1 shared publication - Congrui Hetang
Columbia University Carnegie Mellon University Carnegie Mellon University University of Michigan Carnegie Mellon University
1 shared publication - Jianing Qian
Carnegie Mellon University
1 shared publication - Qi Lyu
Department of Computational Mathematics, Science, and Engineering, Michigan State University, East Lansing, MI 48824, USA
1 shared publication - Tianwei Yue
Carnegie Mellon University Carnegie Mellon University Columbia University Carnegie Mellon University Carnegie Mellon University Carnegie Mellon University
1 shared publication - Wenping Wang
Carnegie Mellon University Carnegie Mellon University Columbia University Carnegie Mellon University Carnegie Mellon University Carnegie Mellon University
1 shared publication
Latest Publications
- Open Access
Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%.
Open AccessDepth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks
Very deep convolutional neural networks (CNNs) have been firmly established as the primary methods for many computer vision tasks. However, most state-of-the-art CNNs are large, which results in high inference latency. Recently, depth-wise separable convolution has been proposed for image recognition tasks on computationally limited platforms such as robotics and self-driving cars. Though it is much faster than its counterpart, regular convolution, accuracy is sacrificed. In this paper, we propose a novel decomposition approach based on SVD, namely depth-wise decomposition, for expanding regular convolutions into depthwise separable convolutions while maintaining high accuracy. We show our approach can be further generalized to the multi-channel and multi-layer cases, based on Generalized Singular Value Decomposition (GSVD) [59]. We conduct thorough experiments with the latest ShuffleNet V2 model [47] on both random synthesized dataset and a large-scale image recognition dataset: ImageNet [10]. Our approach outperforms channel decomposition [73] on all datasets. More importantly, our approach improves the Top-1 accuracy of ShuffleNet V2 by ~2%.