Results 141 to 150 of about 4,886 (174)
Some of the next articles are maybe not open access.
A Study of Image Recognition for Standard Convolution and Depthwise Separable Convolution
2020Artificial intelligence and deep learning techniques are all around our life. Image recognition and natural language processing are the two major topics. Through using TensorFlow-GPU as backend in convolutional neural network (CNN) and deep learning network, image recognition has been an extreme breakthrough in recent years.
Fan-Hsun Tseng, Fan-Yi Kao
openaire +2 more sources
Depthwise Separable Temporal Convolutional Network for Action Segmentation
2020 International Conference on 3D Vision (3DV), 2020Fine-grained temporal action segmentation in long, untrimmed RGB videos is a key topic in visual human-machine interaction. Recent temporal convolution based approaches either use encoder-decoder(ED) architecture or dilations with doubling factor in consecutive convolution layers to segment actions in videos. However ED networks operate on low temporal
Basavaraj Hampiholi +3 more
openaire +2 more sources
Cucumber Disease Recognition Based on Depthwise Separable Convolution
2020Cucumber disease seriously affects the yield and quality of cucumber planting, so quickly and accurately identifying the type of cucumber disease is the premise of cucumber disease control. In view of the complexity of feature extraction in existing cucumber disease recognition methods based on disease leaf image, and the vulnerability of extracted ...
Xianfeng Wang +2 more
openaire +2 more sources
Deep Residual Networks with Pyramid Depthwise Separable Convolution
IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society, 2019Convolutional neural networks (CNNs) have shown remarkable performance in various computer vision tasks in recent years. However, the increasing model size has raised challenges in adopting them in real-time applications as well as mobile or embedded vision applications.
Van-Thanh Hoang +2 more
openaire +1 more source
Fast Depthwise Separable Convolution for Embedded Systems
2018Convolutional neural networks (CNNs) have achieved outstanding performance in many applications. However, as the total number of layers has increased and the model structure has become compound, the computational cost comes into question. The large models cannot operate in embedded or mobile environments where hardware resources are quite limited.
Byeongheon Yoo +2 more
openaire +2 more sources
Reducing SqueezeNet Storage Size with Depthwise Separable Convolutions
2018 International Joint Conference on Neural Networks (IJCNN), 2018Current research in the field of convolutional neu-ral networks usually focuses on improving network accuracy, regardless of the network size and inference time. In this paper, we investigate the effects of storage space reduction in SqueezeNet as it relates to inference time when processing single test samples. In order to reduce the storage space, we
Aline Gondim Santos +5 more
openaire +2 more sources
Wafer Map Defect Classification with Depthwise Separable Convolutions
2020 IEEE International Conference on Consumer Electronics (ICCE), 2020In the IC design process, the test process is the main factor of production cost. Existing tests rely on additional analysis of testing result data by the engineer to determine the status of the process. Thus it could take an additional amount of time and cannot make adjustments of the process immediately. Wafer map defect recognition is an import part
Tsung-Han Tsai, Yu-Chen Lee
openaire +2 more sources
A Depthwise Separable Convolution Architecture for CNN Accelerator
2020 IEEE Applied Signal Processing Conference (ASPCON), 2020Convolutional Neural Network (CNN) give an unmatched performance in image classification, object detection and object tracking. As many of the modern embedded systems for portable devices deals with similar tasks, they often deploy CNN based algorithms.
Harsh Srivastava, Kishor Sarawadekar
openaire +1 more source
Depthwise Separable Convolutional Neural Network for Image Forensics
2019 IEEE Visual Communications and Image Processing (VCIP), 2019General-purpose forensics on small image patches appears to be feasible and important, but in fact poses a challenge due to insufficient statistics. Furthermore, there is a need to develop a forensic approach that can automatically learn effective and robust features related to image forensics with high parameter efficiency. In this paper, we propose a
Yifang Chen 0002 +3 more
openaire +2 more sources
Depthwise Separable Convolutions and Variational Dropout within the context of YOLOv3
2020Deep learning algorithms have demonstrated remarkable performance in many sectors and have become one of the main foundations of modern computer-vision solutions. However, these algorithms often impose prohibitive levels of memory and computational overhead, especially in resource-constrained environments. In this study, we combine the state-of-the-art
Joseph Chakar +2 more
openaire +1 more source