Bo Li

Prof. Dr. Bo Li

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
1 January 2016 in Graphical Models
Verified
Journal Article
Closed access
Bo LiBo Li
Bo Li
HJHenry Johan
Henry Johan
YYYuxiang Ye
Yuxiang Ye
YLYijuan Lu
Yijuan Lu

16 December 2016 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
Bo LiBo Li
Bo Li
YLYijuan Lu
Yijuan Lu
HJHenry Johan
Henry Johan
RFRibel Fares
Ribel Fares

15 July 2020 in International Journal of Speech Technology
Verified
Journal Article
Closed access
PDF file
WWWei Wang
Wei Wang
Paul WattersPaul Watters
Paul Watters
XCXinyi Cao
Xinyi Cao
LSLingjie Shen
Lingjie Shen
Bo LiBo Li
Bo Li

11 November 2020 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
Bo LiBo Li
Bo Li
JYJuefei Yuan
Juefei Yuan
YYYuxiang Ye
Yuxiang Ye
YLYijuan Lu
Yijuan Lu
CZChaoyang (Joe) Zhang
Chaoyang (Joe) Zhang
QTQi Tian
Qi Tian

27 February 2021 in Multimedia Tools and Applications
Verified
Journal Article
Closed access
PDF file
JYJuefei Yuan
Juefei Yuan
HAHameed Abdul-Rashid
Hameed Abdul-Rashid
Bo LiBo Li
Bo Li

7 September 2018 in arXiv
Verified
Preprint
Open access
PDF file
TWTianyang Wang
Tianyang Wang
JHJun Huan
Jun Huan
Bo LiBo Li
Bo Li
Deep learning models learn to fit training data while they are highly expected to generalize well to testing data. Most works aim at finding such models by creatively designing architectures and fine-tuning parameters. To adapt to particular tasks, hand-crafted information such as image prior has also been incorporated into end-to-end learning. However, very little progress has been made on investigating how an individual training sample will influence the generalization ability of a model. In other words, to achieve high generalization accuracy, do we really need all the samples in a training dataset? In this paper, we demonstrate that deep learning models such as convolutional neural networks may not favor all training samples, and generalization accuracy can be further improved by dropping those unfavorable samples. Specifically, the influence of removing a training sample is quantifiable, and we propose a Two-Round Training approach, aiming to achieve higher generalization accuracy. We locate unfavorable samples after the first round of training, and then retrain the model from scratch with the reduced training dataset in the second round. Since our approach is essentially different from fine-tuning or further training, the computational cost should not be a concern. Our extensive experimental results indicate that, with identical settings, the proposed approach can boost performance of the well-known networks on both high-level computer vision problems such as image classification, and low-level vision problems such as image denoising.