Compact Feature Representation for Image Classification Using ELMs

Cui, Dongshun; Zhang, Guanghao; Han, Wei

doi:10.1109/iccvw.2017.124

Cited by 15 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 15 presents accuracy results using the MNIST dataset for handwritten digit recognition done by [24], [77], [34], [76], [74], [75], [29], [30], [27], and [28] [29]. Regarding to the testing time, the work done by [76] also presented the best performance (0.89 seconds).…”

Section: Rq 3: Which Are the Main Findings When Applying Celm In Problems Based On Image Analysis?mentioning

confidence: 99%

See 1 more Smart Citation

Convolutional Extreme Learning Machines: A Systematic Review

Rodrigues¹,

Rogério²,

Kelner³

et al. 2021

Preprint

View full text Add to dashboard Cite

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

show abstract

Section: Rq 3: Which Are the Main Findings When Applying Celm In Problems Based On Image Analysis?mentioning

confidence: 99%

“…Authors in [34] use an approach to the representation of features based on the PCANet network and ELM autoencoder. The proposed architecture aims to understand and extract features for the most diverse applications with low computational cost.…”

Section: Fast Training Of Cnns Using Elm Conceptsmentioning

confidence: 99%

Convolutional Extreme Learning Machines: A Systematic Review

Rodrigues¹,

Rogério²,

Kelner³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Chapter 5 uses the material from References [45,55]. We propose a novel feature representation method named CFR-ELM by using ELM-AE for image classification.…”

Section: Thesis Overviewmentioning

confidence: 99%

“…ELM is a single-hidden-layer forward neural network, which is proposed to break the "barriers between conventional artificial learning techniques and biological learning mechanism" by Huang et al [154]. There are many ELM variants like basic regularized extreme learning (regularized ELM [30]), online sequential extreme learning machine (OS-ELM [73,74]), extreme learning machine autoencoder(ELM-AE [35,55]), local receptive fields based extreme learning machine (ELM-LRF [34]), and so on. In this chapter, the regularized ELM is adopted and evaluated which has three key techniques:…”

Section: Basic Regularized Extreme Learning Machinementioning

confidence: 99%

See 1 more Smart Citation

Enhanced extreme learning machines for image classification

Cui¹

Self Cite

View full text Add to dashboard Cite

First, I would like to thank my supervisor Prof. Huang Guang-Bin for his support and excellent supervision. Thank you for helping me overcome the life and academic obstacles I met these years, and providing help in research thinking and art sense. I will always remember the good advice I have received from you these years. I am also grateful to my co-supervisor Assoc. Prof. Zhang Jie and Assoc. Prof. Lin Zhiping who have given me their kind supervision. Thank you for your time spent on helping me find my way to be a researcher. Great thanks to my project leader, Dr. Yang Yan, who has always been leading me to a young professional researcher when I was in BMW-NTU Future Mobility Lab. She is enthusiastic and always prepared whenever I have questions, and I cannot achieve such works without her help in my first year here. Special thanks to Dr.

show abstract