Multi-View CNN Feature Aggregation with ELM Auto-Encoder for 3D Shape Recognition

Yang, Zhixin; Tang, Lulu; Zhang, Kun; Wong, Pak Kin

doi:10.1007/s12559-018-9598-1

Cited by 46 publications

(18 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the data was trained and classified with an ELM. The authors in [96] presented a computationally efficient method for image recognition. A new structure of multi-view CNNs and ELM-AE has been developed, which uses the composite advantages of VGG-19 deep architecture with the robust representation of ELM-AE features and the fast ELM classifier.…”

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

“…ResNet uses a signal that is the sum of the signal produced by the two previous convolutional layers plus the signal transmitted directly from the point before these layers. We found some works that used ResNet for transfer learning using the pre-trained weights from ILSVRC dataset in conjunction with ELM: [31], [115], [100], [66], [96].…”

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

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: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

confidence: 99%

Section: Pre-trained Cnn In Other Application Domain For Feature Extraction and Elm For Fast Learningmentioning

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

“…Nowadays, ELM series methods are applied in various scenarios including regression and classification, by accelerating computation significantly while keeping convincing performance at the same time [15]- [17], [29], [54]. The major driving force underneath is ELM omitting back-propagations compared with traditional deep learning methods.…”

Section: B Extreme Learning Machine (Elm)mentioning

confidence: 99%

An ELM-Embedded Deep Learning Based Intelligent Recognition System for Computer Numeric Control Machine Tools

et al. 2020

Self Cite

View full text Add to dashboard Cite

In modern manufacturing industry featured with automation and flexibility, the intelligent tool management for Computer Numeric Control (CNC) machine plays an essential role in manufacturing automation. The automatic tool recognition in terms of geometric shapes, materials and usage functions could facilitate the seamless integration with downstream process planning and scheduling processes. In this paper, a intelligent tool recognition system is proposed with a novel hybrid framework of multi-channel deep learning network with non-iterative and fast feedforward neural network to meet high efficiency and accuracy requirement in intelligent manufacturing. The combination of the fine-tuning Convolutional Neural Networks (CNNs) with the random parameter assignment mechanism of Extreme Learning Machines (ELMs) reach a balance in accurate feature extraction and fast recognition. In the proposed hybrid framework, features extracted from efficient CNNs are aggregated into robust ELM auto-encoders (ELM-AEs) to generate the compact but rich feature information, which are then feed to the subsequent single layer ELM network for tool recognition. The performance of proposed framework is verified on several standardized 3D shape retrieval and classification dataset, as well as on a self-constructed multi-view 3D data represented tool library database. Numerical experiments reveal a promising application perspective of proposed intelligent recognition system on manufacturing automation. INDEX TERMS CNC tool recognition, hybrid deep learning networks, convolutional neural networks, extreme learning machines auto-encode, tool library database.

show abstract

“…Self-supervised learning: First of all, the bias between mixed classification performance on "old" classes and "novel" classes are largely alleviated due to the use of self-supervision, as the discrepancy, i.e., the classification accuracy gap between "old" classes and "novel" classes, 8.90% of proposed and 12.54% of variant (7) are lower than 18.96% of variant (1). Secondly, it is observed that self-supervised learning can always boost the performance on both clustering and mixed classification for "novel" classes by comparing variant (7) and proposed with variant (1).…”

Section: Ablation Studymentioning

confidence: 99%

“…5.5 Ablation study: Self-supervised learning. For variant (7), the pretraining and fine-tuning schemes in [81] are followed. .…”

mentioning

confidence: 99%