[HTML][HTML] Pruning by explaining: A novel criterion for deep neural network pruning

SK Yeom, P Seegerer, S Lapuschkin, A Binder… - Pattern Recognition, 2021 - Elsevier
The success of convolutional neural networks (CNNs) in various applications is
accompanied by a significant increase in computation and parameter storage costs. Recent …

Energy efficient clustering protocol for FANETS using moth flame optimization

S Bharany, S Sharma, S Bhatia, MKI Rahmani… - Sustainability, 2022 - mdpi.com
FANET (flying ad-hoc networks) is currently a trending research topic. Unmanned aerial
vehicles (UAVs) have two significant challenges: short flight times and inefficient routing due …

Autopruner: An end-to-end trainable filter pruning method for efficient deep model inference

JH Luo, J Wu - Pattern Recognition, 2020 - Elsevier
Channel pruning is an important method to speed up CNN model's inference. Previous filter
pruning algorithms regard importance evaluation and model fine-tuning as two independent …

[HTML][HTML] A bibliometric analysis of off-line handwritten document analysis literature (1990–2020)

V Ruiz-Parrado, R Heradio, E Aranda-Escolastico… - Pattern Recognition, 2022 - Elsevier
Providing computers with the ability to process handwriting is both important and
challenging, since many difficulties (eg, different writing styles, alphabets, languages, etc.) …

Benchmarking chinese text recognition: Datasets, baselines, and an empirical study

H Yu, J Chen, B Li, J Ma, M Guan, X Xu, X Wang… - arXiv preprint arXiv …, 2021 - arxiv.org
The flourishing blossom of deep learning has witnessed the rapid development of text
recognition in recent years. However, the existing text recognition methods are mainly …

Online multi-granularity distillation for gan compression

Y Ren, J Wu, X Xiao, J Yang - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Abstract Generative Adversarial Networks (GANs) have witnessed prevailing success in
yielding outstanding images, however, they are burdensome to deploy on resource …

A compact convolutional neural network augmented with multiscale feature extraction of acquired monitoring data for mechanical intelligent fault diagnosis

K Zhang, J Chen, T Zhang, Z Zhou - Journal of Manufacturing Systems, 2020 - Elsevier
Considering all the monitoring data of bearings until failure, very few data are acquired
when the bearings are faulty. Such circumstance leads to small faulty sample problem when …

Literature review of deep learning research areas

MM Yapıcı, A Tekerek, N Topaloğlu - Gazi Mühendislik Bilimleri …, 2019 - dergipark.org.tr
Deep learning (DL) is a powerful machine learning field that has achieved considerable
success in many research areas. Especially in the last decade, the-state-of-the-art studies …

Handwritten Urdu characters and digits recognition using transfer learning and augmentation with AlexNet

A Rasheed, N Ali, B Zafar, A Shabbir, M Sajid… - IEEE …, 2022 - ieeexplore.ieee.org
Automated recognition of handwritten characters and digits is a challenging task. Although a
significant amount of literature exists for automatic recognition of handwritten characters of …

Deep learning-based data augmentation method and signature verification system for offline handwritten signature

MM Yapıcı, A Tekerek, N Topaloğlu - Pattern Analysis and Applications, 2021 - Springer
Offline handwritten signature verification is a challenging pattern recognition task. One of the
most significant limitations of the handwritten signature verification problem is inadequate …