Zhiyong Gan

Zhiyong Gan

Auto-generated profile, based on publicly available information

Zhiyong Gan

China United Network Communications Corporation Limited Guangdong Branch, Guangzhou, China

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
28 October 2024
Verified
Conference Paper
Open access
JCJiankang Chen
Jiankang Chen
LDLing Deng
Ling Deng
ZGZhiyong Gan
Zhiyong Gan
WZWei-Shi Zheng
Wei-Shi Zheng
RWRuixuan Wang
Ruixuan Wang
Out-of-Distribution (OOD) detection is crucial when deploying machine learning models in open-world applications. The core challenge in OOD detection is mitigating the model's overconfidence on OOD data. While recent methods using auxiliary outlier datasets or synthesizing outlier features have shown promising OOD detection performance, they are limited due to costly data collection or simplified assumptions. In this paper, we propose a novel OOD detection framework FodFoM that innovatively combines multiple foundation models to generate two types of challenging fake outlier images for classifier training. The first type is based on BLIP-2's image captioning capability, CLIP's vision-language knowledge, and Stable Diffusion's image generation ability. Jointly utilizing these foundation models constructs fake outlier images which are semantically similar to but different from in-distribution (ID) images. For the second type, GroundingDINO's object detection ability is utilized to help construct pure background images by blurring foreground ID objects in ID images. The proposed framework can be flexibly combined with multiple existing OOD detection methods. Extensive empirical evaluations show that image classifiers with the help of constructed fake images can more accurately differentiate real OOD image from ID ones. New state-of-the-art OOD detection performance is achieved on multiple benchmarks. The code is available at https://github.com/Cverchen/ACMMM2024-FodFoM.

27 October 2025
Verified
Conference Paper
Open access
FYFan Yang
Fan Yang
LDLing Deng
Ling Deng
ZGZhiyong Gan
Zhiyong Gan
QHQisheng He
Qisheng He
YFYuanbo Fang
Yuanbo Fang
TCTianshui Chen
Tianshui Chen

1 November 2021 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
KWKun Wang
Kun Wang
GYGuochao Yang
Guochao Yang
BCBaohua Cheng
Baohua Cheng
ZGZhiyong Gan
Zhiyong Gan
YQYan Qi
Yan Qi
JBJiang Bian
Jiang Bian
This paper analyzes the energy saving effect and optimal operation of the integrated park type energy system. The park type integrated energy system includes photovoltaic power generation system, ground source heat pump system, solar air conditioning system, regenerative electric boiler system and solar hot water system and so on. The energy saving benefit calculation model of each subsystem is established, and according to the operation history data of each subsystem, the calculation results of each subsystem are analyzed. It shows that: The energy saving income of photovoltaic power generation system is 734,200 yuan/year. The main revenue comes from the second and third quarters, during which it should pay attention to the maintenance of photovoltaic modules to ensure the maximum energy saving benefit. The energy saving income of ground source heat pump system in summer is 155,900 yuan/year, and the energy saving effect is not significant. It can cooperate with traditional units for cooling in summer. The heating in winter in the park is provided by ground source heat pump system, regenerative electric boiler system and solar energy air conditioning system. Its energy saving benefit is 3.995 million yuan/year which is the main source of energy saving income in the park, with remarkable energy saving effect.

5 September 2025 in Pattern Recognition
Verified
Journal Article
Closed access
GZGege Zhang
Gege Zhang
ZGZhiyong Gan
Zhiyong Gan
LDLing Deng
Ling Deng
SNShuaicheng Niu
Shuaicheng Niu
ZPZhenghua Peng
Zhenghua Peng
XXXiangmin Xu
Xiangmin Xu