Randomly translational activation inspired by the input distributions of ReLU
Authors:
- Jiale CaoJCJiale Cao
- Yanwei PangYPYanwei Pang
- Xuelong LiXLXuelong Li
- Jingkun LiangJLJingkun Liang
- 1 January 2018
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 275, 859-868
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (61632081, 61761130079)
This publication has 12 references indexed in Scilit:
- Learning Multilayer Channel Features for Pedestrian DetectionIEEE Transactions on Image Processing, 2017
- Combining local and global hypotheses in deep neural network for multi-label image classificationNeurocomputing, 2017
- CNN for saliency detection with low-level feature integrationNeurocomputing, 2017
- Multi-feature fusion deep networksNeurocomputing, 2016
- A Universal Framework for Salient Object DetectionIEEE Transactions on Multimedia, 2016
- Speed up deep neural network based pedestrian detection by sharing features across multi-scale modelsNeurocomputing, 2016
- DISC: Deep Image Saliency Computing via Progressive Representation LearningIEEE Transactions on Neural Networks and Learning Systems, 2016
- Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency MiningIEEE Transactions on Neural Networks and Learning Systems, 2015
- Deep learningNature, 2015
- Region-Based Object Recognition by Color Segmentation Using a Simplified PCNNIEEE Transactions on Neural Networks and Learning Systems, 2014