Viet-Hung Tran

Viet-Hung Tran

Auto-generated profile, based on publicly available information

Viet-Hung Tran

School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast , Belfast BT9 5BN

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 January 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
NTNgoc-Trung Tran
Ngoc-Trung Tran
VTViet-Hung Tran
Viet-Hung Tran
NNNgoc-Bao Nguyen
Ngoc-Bao Nguyen
TNTrung-Kien Nguyen
Trung-Kien Nguyen
Ngai-Man CheungNgai-Man Cheung
Ngai-Man Cheung
Recent successes in Generative Adversarial Networks (GAN) have affirmed the importance of using more data in GAN training. Yet it is expensive to collect data in many domains such as medical applications. Data Augmentation (DA) has been applied in these applications. In this work, we first argue that the classical DA approach could mislead the generator to learn the distribution of the augmented data, which could be different from that of the original data. We then propose a principled framework, termed Data Augmentation Optimized for GAN (DAG), to enable the use of augmented data in GAN training to improve the learning of the original distribution. We provide theoretical analysis to show that using our proposed DAG aligns with the original GAN in minimizing the Jensen-Shannon (JS) divergence between the original distribution and model distribution. Importantly, the proposed DAG effectively leverages the augmented data to improve the learning of discriminator and generator. We conduct experiments to apply DAG to different GAN models: unconditional GAN, conditional GAN, self-supervised GAN and CycleGAN using datasets of natural images and medical images. The results show that DAG achieves consistent and considerable improvements across these models. Furthermore, when DAG is used in some GAN models, the system establishes state-of-the-art Fréchet Inception Distance (FID) scores. Our code is available (https://github.com/tntrung/dag-gans).

6 January 2026 in RAS Techniques and Instruments
Verified
Journal Article
Open access
DMDylan Magill
Dylan Magill
MNM Nicholl
M Nicholl
VAV Anilkumar
V Anilkumar
SVS van Velzen
S van Velzen
XSX Sheng
X Sheng
JWJ Weston
J Weston
The Vera C. Rubin Observatory’s 10-yr Legacy Survey of Space and Time (LSST) is expected to produce a hundredfold increase in the number of transients we observe. However, there are insufficient spectroscopic resources to follow up on all of the wealth of targets that LSST will provide. As such it is necessary to be able to prioritize objects for follow-up observations or inclusion in sample studies based purely on their LSST photometry. We are particularly keen to identify tidal disruption events (TDEs) with LSST. TDEs are immensely useful for determining black hole parameters and probing our understanding of accretion physics. To assist in these efforts, we present the Many Artificial LSST Light curves based on the Observations of Real Nuclear transients (MALLORN) data set and the corresponding classifier challenge for identifying TDEs. MALLORN comprises 10 178 simulated LSST light curves, constructed from real Zwicky Transient Facility (ZTF) observations of 64 TDEs, 727 nuclear supernovae and 1407 AGN with spectroscopic labels using Gaussian process fitting, empirically motivated spectral energy distributions from SNCosmo and the baseline from the Rubin Survey Simulator. Our novel approach can be easily adapted to simulate transients for any photometric survey using observations from another, requiring only the limiting magnitudes and an estimate of the cadence of observations. The MALLORN Astronomical Classification Challenge, launched on Kaggle on 2025 October 15, will allow competitors to test their photometric classifiers on simulated LSST data to find TDEs and improve upon their capabilities prior to the start of LSST.