most citedCompacting, Picking and Growing for Unforgetting Continual Learning

133 citations · 134 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG2019133 cited

Compacting, Picking and Growing for Unforgetting Continual Learning

Steven C. Y. Hung, Cheng-Hao Tu, Cheng-En Wu +3

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the prin…

cs.CV20191 cited

IMMVP: An Efficient Daytime and Nighttime On-Road Object Detector

Cheng-En Wu, Yi-Ming Chan, Chien-Hung Chen +2

It is hard to detect on-road objects under various lighting conditions. To improve the quality of the classifier, three techniques are used. We define subclasses to separate daytim…

cs.CV2018

Data-specific Adaptive Threshold for Face Recognition and Authentication

Hsin-Rung Chou, Jia-Hong Lee, Yi-Ming Chan +1

Many face recognition systems boost the performance using deep learning models, but only a few researches go into the mechanisms for dealing with online registration. Although we c…

cs.CV2018

Joint Estimation of Age and Gender from Unconstrained Face Images using Lightweight Multi-task CNN for Mobile Applications

Jia-Hong Lee, Yi-Ming Chan, Ting-Yen Chen +1

Automatic age and gender classification based on unconstrained images has become essential techniques on mobile devices. With limited computing power, how to develop a robust syste…

cs.CV2018

Unifying and Merging Well-trained Deep Neural Networks for Inference Stage

Yi-Min Chou, Yi-Ming Chan, Jia-Hong Lee +2

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different ta…