91 citations · 98 across the 11 of their papers we have counts for
11 papers
Making the Invisible Visible: Toward High-Quality Terahertz Tomographic Imaging via Physics-Guided Restoration
Weng-Tai Su, Yi-Chun Hung, Po-Jen Yu +2
Terahertz (THz) tomographic imaging has recently attracted significant attention thanks to its non-invasive, non-destructive, non-ionizing, material-classification, and ultra-fast…
Kinship Representation Learning with Face Componential Relation
Weng-Tai Su, Min-Hung Chen, Chien-Yi Wang +2
Kinship recognition aims to determine whether the subjects in two facial images are kin or non-kin, which is an emerging and challenging problem. However, most previous methods foc…
Physics-guided Terahertz Computational Imaging
Weng-Tai Su, Yi-Chun Hung, Po-Jen Yu +2
Visualizing information inside objects is an ever-lasting need to bridge the world from physics, chemistry, biology to computation. Among all tomographic techniques, terahertz (THz…
Keeping Deep Lithography Simulators Updated: Global-Local Shape-Based Novelty Detection and Active Learning
Hao-Chiang Shao, Hsing-Lei Ping, Kuo-shiuan Chen +5
Learning-based pre-simulation (i.e., layout-to-fabrication) models have been proposed to predict the fabrication-induced shape deformation from an IC layout to its fabricated circu…
Ensemble Learning with Manifold-Based Data Splitting for Noisy Label Correction
Hao-Chiang Shao, Hsin-Chieh Wang, Weng-Tai Su +1
Label noise in training data can significantly degrade a model's generalization performance for supervised learning tasks. Here we focus on the problem that noisy labels are primar…
Seeing through a Black Box: Toward High-Quality Terahertz TomographicImaging via Multi-Scale Spatio-Spectral Image Fusion
Weng-tai Su, Yi-Chun Hung, Ta-Hsuan Chao +3
Terahertz (THz) imaging has recently attracted significant attention thanks to its non-invasive, non-destructive, non-ionizing, material-classification, and ultra-fast nature for o…
Graph Neural Net using Analytical Graph Filters and Topology Optimization for Image Denoising
Weng-tai Su, Gene Cheung, Richard Wildes +1
While convolutional neural nets (CNNs) have achieved remarkable performance for a wide range of inverse imaging applications, the filter coefficients are computed in a purely data-…
SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination
Chih-Chung Hsu, Chia-Wen Lin, Weng-Tai Su +1
Despite generative adversarial networks (GANs) can hallucinate photo-realistic high-resolution (HR) faces from low-resolution (LR) faces, they cannot guarantee preserving the ident…
Graph-based Joint Signal / Power Restoration for Energy Harvesting Wireless Sensor Networks
Megumi Kaneko, Gene Cheung, Weng-tai Su +1
The design of energy and spectrally efficient Wireless Sensor Networks (WSN) is crucial to support the upcoming expansion of IoT/M2M mobile data traffic. In this work, we consider…
Graph Fourier Transform with Negative Edges for Depth Image Coding
Weng-Tai Su, Gene Cheung, Chia-Wen Lin
Recent advent in graph signal processing (GSP) has led to the development of new graph-based transforms and wavelets for image / video coding, where the underlying graph describes…
Robust Semi-Supervised Graph Classifier Learning with Negative Edge Weights
Gene Cheung, Weng-Tai Su, Yu Mao +1
In a semi-supervised learning scenario, (possibly noisy) partially observed labels are used as input to train a classifier, in order to assign labels to unclassified samples. In th…