Zhijun Tan

Prof. Zhijun Tan


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
24 September 2016 in Journal of Scientific Computing
Verified
Journal Article
Closed access
PDF file
DHDaozhi Han
Daozhi Han
ABAlex Brylev
Alex Brylev
Xiaofeng YangXiaofeng Yang
Xiaofeng Yang
ZTZhijun Tan
Zhijun Tan

16 December 2024 in Computer Methods in Applied Mechanics and Engineering
Verified
Journal Article
Closed access
HLHongji Li
Hongji Li
HFHaolong Fan
Haolong Fan
ZTZhijun Tan
Zhijun Tan

29 January 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
ZSZhuohao Sun
Zhuohao Sun
YQYiqiao Qiu
Yiqiao Qiu
ZTZhijun Tan
Zhijun Tan
WZWeishi Zheng
Weishi Zheng
RWRuixuan Wang
Ruixuan Wang
Out-of-distribution (OOD) detection is essential when deploying neural networks in the real world. One main challenge is that neural networks often make overconfident predictions on OOD data. In this study, we propose an effective post-hoc OOD detection method, named HIMPLoS, based on a new feature masking strategy and a novel logit smoothing strategy. Feature masking determines the important features at the penultimate layer for each in-distribution (ID) class based on the weights of the ID class in the classifier head and masks the rest features. Logit smoothing computes the cosine similarity between the feature vector of the test sample and the prototype of the predicted ID class at the penultimate layer and uses the similarity as an adaptive temperature factor on the logit to alleviate the network’s overconfidence prediction for OOD data. With these strategies, we can reduce feature activation of OOD data and enlarge the gap in OOD score between ID and OOD data. Extensive experiments on multiple standard OOD detection benchmarks demonstrate the effectiveness of our method and its compatibility with existing methods, with new state-of-the-art performance achieved from our method. The source code will be released publicly.

1 January 2011 in Communications in Computational Physics
Verified
Journal Article
Closed access
PDF file
ZTZhijun Tan
Zhijun Tan
KLKian Meng Lim
Kian Meng Lim
BKBoo Cheong Khoo
Boo Cheong Khoo
An Implementation of MAC Grid-Based IIM-Stokes Solver for Incompressible Two-Phase Flows - Volume 10 Issue 5 - Zhijun Tan, K. M. Lim, B. C. Khoo

23 February 2022 in Engineering with Computers
Verified
Journal Article
Closed access
PDF file
JYJunxiang Yang
Junxiang Yang
JCJianjun Chen
Jianjun Chen
ZTZhijun Tan
Zhijun Tan

21 October 2024 in Computers & Mathematics with Applications
Verified
Journal Article
Closed access
ZTZhijun Tan
Zhijun Tan