Object recognition from 3D depth data with Extreme Learning Machine and Local Receptive Field

Boubou, Somar; Narikiyo, Tatsuo; Kawanishi, Michihiro

doi:10.1109/aim.2017.8014049

Cited by 3 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite not having the same power as the conventional CNNs (with fully connected layers and backpropagation) to extract features, CELM's accuracy proved competitive in the analyzed scenarios and benchmark datasets. The competitiveness of the results is clear when, in many cases, CELM was superior to several traditional models such as MLP (as in [102], [69], [50]) e SVM (as in [46], [113], [90]). Observing these results, we reported a good generalization and good representativeness by CELM [104], [68], [97], [27], [55], [57], [49].…”

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

confidence: 99%

“…Several works applied ELM-LRF in its default form for their learning process [6], [90], [25], [63], [39], [53], and [52]; and some other variations of ELM-LRF, as shown in Table 10. Some works consider using multiple data sources for parallel feature extraction with ELM-LRF for making a unique final decision.…”

Section: Random Filtermentioning

confidence: 99%

“…On the other hand, the training and testing time was not clear due to the missing reported results. Table 17 shows the results when solving RGB-D image recognition using the Washington RGB-D Object dataset by the works [90], [91], [93], [92], and [94]. RGB-D image recognition is a task that considers two types of data, such as the RGB color channel and the depth, which makes the classification task harder.…”

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

confidence: 99%

“…Besides the high complexity for RGB-D classification, the CELM architectures reached good accuracy. Besides provided a low accuracy, the work presented in [90] reached the best training time due to its network complexity (192.51 seconds). [94] VGGNet-ELM 91.10 --…”

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

confidence: 99%

See 3 more Smart Citations

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%

Section: Random Filtermentioning

confidence: 99%

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

confidence: 99%

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

confidence: 99%

See 2 more Smart Citations

Convolutional Extreme Learning Machines: A Systematic Review

Rodrigues¹,

Rogério²,

Kelner³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Several studies have applied the ELM-LRF in its default form for their learning process [6,25,39,52,53,63,90], along with some other variations of ELM-LRF, as shown in Table 10. Some of the studies considered using multiple data sources for parallel feature extraction with the ELM-LRF to make a unique final decision.…”

Section: Cnn With Predefined Kernels For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

Convolutional Extreme Learning Machines: A Systematic Review

et al. 2021

View full text Add to dashboard Cite

Much work has recently identified the need to combine deep learning with extreme learning in order to strike a performance balance with accuracy, especially in the domain of multimedia applications. When considering this new paradigm—namely, the convolutional extreme learning machine (CELM)—we present a systematic review that investigates alternative deep learning architectures that use the extreme learning machine (ELM) for faster training to solve problems that are based on image analysis. We detail each of the architectures that are found in the literature along with their application scenarios, benchmark datasets, main results, and advantages, and then present the open challenges for CELM. We followed a well-structured methodology and established relevant research questions that guided our findings. Based on 81 primary studies, we found that object recognition is the most common problem that is solved by CELM, and CCN with predefined kernels is the most common CELM architecture proposed in the literature. The results from experiments show that CELM models present good precision, convergence, and computational performance, and they are able to decrease the total processing time that is required by the learning process. The results presented in this systematic review are expected to contribute to the research area of CELM, providing a good starting point for dealing with some of the current problems in the analysis of computer vision based on images.

show abstract