arXiv subjects

Guohao Ying

Publications and source records attributed to Guohao Ying.

5 recordsLinked to original sources

arXiv2024

Testing the gauged $\mathrm{U(1)}_{B-L}$ model for loop induced neutrino mass with dark matter

We present a new viable benchmark scenario under the current experimental data for the model which can explain tiny mass of active neutrinos and dark matter, as a summary of our results. Majorana masses of right-handed neutrinos are given by the spontaneous breaking of the $\mathrm{U(1)}_{B-L}$ gauge symmetry above the electroweak scale, and tiny neutrino masses are radiatively induced by quantum effects of particles of the dark sector including dark matter candidates. We first show benchmark points which satisfy current experimental data, and then give comments on how this model can be tested at collider experiments.

hep-ph↗

arXiv2024

Revisiting the model for radiative neutrino masses with dark matter in the $\mathrm{U(1)}_{B-L}$ gauge theory

The radiative seesaw model with gauged $\mathrm{U(1)}_{B-L}\times\mathbb{Z}_2$ extension is a well-motivated scenario which gives consistent predictions of active neutrino masses and the abundance of dark matter. Majorana masses of right-handed neutrinos, the lightest of which can be identified as dark matter, are given by the spontaneous breaking of the $\mathrm{U(1)}_{B-L}$ gauge symmetry. We revisit this model with the latest constraints from dark matter searches, neutrino oscillations, flavor experiments and collider experiments. We explore the feasible parameter space of this model, and find that there are still allowed regions under the latest experimental constraints. We present new viable benchmark scenarios for this model, i.e., the right-handed neutrino dark matter scenario and the scalar dark matter scenario. We also mention the testability of these benchmark scenarios at future experiments.

hep-ph↗

arXiv2022

EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs

Generative adversarial networks (GANs) have proven successful in image generation tasks. However, GAN training is inherently unstable. Although many works try to stabilize it by manually modifying GAN architecture, it requires much expertise. Neural architecture search (NAS) has become an attractive solution to search GANs automatically. The early NAS-GANs search only generators to reduce search complexity but lead to a sub-optimal GAN. Some recent works try to search both generator (G) and discriminator (D), but they suffer from the instability of GAN training. To alleviate the instability, we propose an efficient two-stage evolutionary algorithm-based NAS framework to search GANs, namely EAGAN. We decouple the search of G and D into two stages, where stage-1 searches G with a fixed D and adopts the many-to-one training strategy, and stage-2 searches D with the optimal G found in stage-1 and adopts the one-to-one training and weight-resetting strategies to enhance the stability of GAN training. Both stages use the non-dominated sorting method to produce Pareto-front architectures under multiple objectives (e.g., model size, Inception Score (IS), and Fréchet Inception Distance (FID)). EAGAN is applied to the unconditional image generation task and can efficiently finish the search on the CIFAR-10 dataset in 1.2 GPU days. Our searched GANs achieve competitive results (IS=8.81$\pm$0.10, FID=9.91) on the CIFAR-10 dataset and surpass prior NAS-GANs on the STL-10 dataset (IS=10.44$\pm$0.087, FID=22.18). Source code: https://github.com/marsggbo/EAGAN.

cs.CV↗

arXiv2022

Evolutionary Multi-objective Architecture Search Framework: Application to COVID-19 3D CT Classification

The COVID-19 pandemic has threatened global health. Many studies have applied deep convolutional neural networks (CNN) to recognize COVID-19 based on chest 3D computed tomography (CT). Recent works show that no model generalizes well across CT datasets from different countries, and manually designing models for specific datasets requires expertise; thus, neural architecture search (NAS) that aims to search models automatically has become an attractive solution. To reduce the search cost on large 3D CT datasets, most NAS-based works use the weight-sharing (WS) strategy to make all models share weights within a supernet; however, WS inevitably incurs search instability, leading to inaccurate model estimation. In this work, we propose an efficient Evolutionary Multi-objective ARchitecture Search (EMARS) framework. We propose a new objective, namely potential, which can help exploit promising models to indirectly reduce the number of models involved in weights training, thus alleviating search instability. We demonstrate that under objectives of accuracy and potential, EMARS can balance exploitation and exploration, i.e., reducing search time and finding better models. Our searched models are small and perform better than prior works on three public COVID-19 3D CT datasets.

eess.IV↗

arXiv2019

Better Guider Predicts Future Better: Difference Guided Generative Adversarial Networks

Predicting the future is a fantasy but practicality work. It is the key component to intelligent agents, such as self-driving vehicles, medical monitoring devices and robotics. In this work, we consider generating unseen future frames from previous obeservations, which is notoriously hard due to the uncertainty in frame dynamics. While recent works based on generative adversarial networks (GANs) made remarkable progress, there is still an obstacle for making accurate and realistic predictions. In this paper, we propose a novel GAN based on inter-frame difference to circumvent the difficulties. More specifically, our model is a multi-stage generative network, which is named the Difference Guided Generative Adversarial Netwok (DGGAN). The DGGAN learns to explicitly enforce future-frame predictions that is guided by synthetic inter-frame difference. Given a sequence of frames, DGGAN first uses dual paths to generate meta information. One path, called Coarse Frame Generator, predicts the coarse details about future frames, and the other path, called Difference Guide Generator, generates the difference image which include complementary fine details. Then our coarse details will then be refined via guidance of difference image under the support of GANs. With this model and novel architecture, we achieve state-of-the-art performance for future video prediction on UCF-101, KITTI.

cs.CV↗