Browsing by Author "Fu, Tzu-Chien"

Now showing 1 - 3 of 3

Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation
(2018-01-01)
Liu, Yen-Cheng
;
Yeh, Yu-Ying
;
Fu, Tzu-Chien
;
Wang, Sheng-De
;
Chiu, Wei-Chen
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated. However, one cannot easily address this task without observing ground truth annotation for the training data. To address this problem, we propose a novel deep learning model of Cross-Domain Representation Disentangler (CDRD). By observing fully annotated source-domain data and unlabeled target-domain data of interest, our model bridges the information across data domains and transfers the attribute information accordingly. Thus, cross-domain feature disentanglement and adaptation can be jointly performed. In the experiments, we provide qualitative results to verify our disentanglement capability. Moreover, we further confirm that our model can be applied for solving classification tasks of unsupervised domain adaptation, and performs favorably against state-of-the-art image disentanglement and translation methods.
E-Band RF-to-DC Converter Using Schottky Diode in 0.18-mu m CMOS Technology
(2016)
Chang, Wei-Ling
;
Meng, Chinchun
;
Fu, Tzu-Chien
;
Huang, Guo-Wei
;
電機工程學系
This paper demonstrates a millimeter-wave RF-to-DC converter based on Schottky-barrier diodes using 0.18-mu m CMOS technology. The Schottky-barrier diode has a cutoff frequency of 400 GHz and a low turn-on voltage of 0.3 V. In the RF-to-DC quadrupler, the difference in turn-on voltages between the Schottky-barrier diode and n-well to p-substrate parasitic pn junction prevents the pn junction from turning on with an effect similar to the Schottky diode clamp in Schottky TTL circuits. The input matching has a better than 10 dB return loss from 50 GHz to 100 GHz. The RF-to-DC quadrupler generates a 3.15 V DC voltage at 84 GHz.
LEARNING GUIDED CONVOLUTIONAL NEURAL NETWORKS FOR CROSS-RESOLUTION FACE RECOGNITION
(2017-01-01)
Fu, Tzu-Chien
;
Chiu, Wei-Chen
;
Wang, Yu-Chiang Frank
;
交大名義發表
;
National Chiao Tung University
Cross-resolution face recognition tackles the problem of matching face images with different resolutions. Although state-of-the-art convolutional neural network (CNN) based methods have reported promising performances on standard face recognition problems, such models cannot sufficiently describe images with resolution different from those seen during training, and thus cannot solve the above task accordingly. In this paper, we propose Guided Convolutional Neural Network (Guided-CNN), which is a novel CNN architecture with parallel sub-CNN models as guide and learners. Unique loss functions are introduced, which would serve as joint supervision for images within and across resolutions. Our experiments not only verify the use of our model for cross-resolution recognition, but also its applicability of recognizing face images with different degrees of occlusion.