scispace - formally typeset
S

Sheng Guo

Researcher at Wilmington University

Publications -  45
Citations -  2417

Sheng Guo is an academic researcher from Wilmington University. The author has contributed to research in topics: Convolutional neural network & Contextual image classification. The author has an hindex of 14, co-authored 40 publications receiving 1504 citations. Previous affiliations of Sheng Guo include Chinese Academy of Sciences.

Papers
More filters
Posted ContentDOI

Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

Spyridon Bakas, +438 more
- 05 Nov 2018 - 
TL;DR: This study assesses the state-of-the-art machine learning methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i.e., 2012-2018, and investigates the challenge of identifying the best ML algorithms for each of these tasks.
Posted Content

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

Sheng Guo, +6 more
- 03 Aug 2018 - 
TL;DR: In this paper, a learning curriculum is designed to measure the complexity of data using its distribution density in a feature space, and rank the complexity in an unsupervised manner, resulting in a high-performance CNN model, where the negative impact of noisy labels is reduced substantially.
Book ChapterDOI

CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images

Sheng Guo, +6 more
TL;DR: It is shown by experiments that those images with highly noisy labels can surprisingly improve the generalization capability of model, by serving as a manner of regularization, resulting in a high-performance CNN the model, where the negative impact of noisy labels is reduced substantially.
Journal ArticleDOI

Knowledge Guided Disambiguation for Large-Scale Scene Classification With Multi-Resolution CNNs

Limin Wang, +4 more
- 01 Apr 2017 - 
TL;DR: Wang et al. as mentioned in this paper proposed a multi-resolution CNN architecture that captures visual content and structure at multiple levels and designed two knowledge guided disambiguation techniques to deal with the problem of label ambiguity.
Posted Content

Places205-VGGNet Models for Scene Recognition

Limin Wang, +3 more
- 07 Aug 2015 - 
TL;DR: This report describes the implementation of training the VGGNets on the large-scale Places205 dataset by using a Multi-GPU extension of Caffe toolbox with high computational efficiency and achieves the state-of-the-art performance of trained models on three datasets.