Search Results for author: Chun-Nan Chou

Found 8 papers, 0 papers with code

G2R Bound: A Generalization Bound for Supervised Learning from GAN-Synthetic Data

no code implementations29 May 2019 Fu-Chieh Chang, Hao-Jen Wang, Chun-Nan Chou, Edward Y. Chang

Performing supervised learning from the data synthesized by using Generative Adversarial Networks (GANs), dubbed GAN-synthetic data, has two important applications.

General Classification

MBS: Macroblock Scaling for CNN Model Reduction

no code implementations CVPR 2019 Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang

In this paper we propose the macroblock scaling (MBS) algorithm, which can be applied to various CNN architectures to reduce their model size.

BRIEF: Backward Reduction of CNNs with Information Flow Analysis

no code implementations16 Jul 2018 Yu-Hsun Lin, Chun-Nan Chou, Edward Y. Chang

This paper proposes BRIEF, a backward reduction algorithm that explores compact CNN-model designs from the information flow perspective.

EA-CG: An Approximate Second-Order Method for Training Fully-Connected Neural Networks

no code implementations19 Feb 2018 Sheng-Wei Chen, Chun-Nan Chou, Edward Y. Chang

For training fully-connected neural networks (FCNNs), we propose a practical approximate second-order method including: 1) an approximation of the Hessian matrix and 2) a conjugate gradient (CG) based method.

Distributed Training Large-Scale Deep Architectures

no code implementations10 Aug 2017 Shang-Xuan Zou, Chun-Yen Chen, Jui-Lin Wu, Chun-Nan Chou, Chia-Chin Tsao, Kuan-Chieh Tung, Ting-Wei Lin, Cheng-Lung Sung, Edward Y. Chang

Scale of data and scale of computation infrastructures together enable the current deep learning renaissance.

Representation Learning on Large and Small Data

no code implementations25 Jul 2017 Chun-Nan Chou, Chuen-Kai Shie, Fu-Chieh Chang, Jocelyn Chang, Edward Y. Chang

Deep learning owes its success to three key factors: scale of data, enhanced models to learn representations from data, and scale of computation.

Representation Learning Small Data Image Classification

CLKN: Cascaded Lucas-Kanade Networks for Image Alignment

no code implementations CVPR 2017 Che-Han Chang, Chun-Nan Chou, Edward Y. Chang

The main component of this architecture is a Lucas-Kanade layer that performs the inverse compositional algorithm on convolutional feature maps.

Homography Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.