Distributed Deep Learning of ResNet50 and VGG16 with Pipeline Parallelism

Small objects in traffic scenes are difficult to detect. To improve the accuracy of small object detection using images taken by unmanned aerial vehicles (UAV), this study proposes a feature-enhancement detection algorithm based on a single shot multibox detector (SSD), named composite backbone single shot multibox detector (CBSSD), which uses a composite connection backbone to enhance feature representation. First, to enhance the detection effect of small objects, the lead backbone network, VGG16, is kept constant, and ResNet50 is added as an assistant backbone network, and the residual structure in ResNet50 is used to obtain lower feature information. The obtained lower feature information is then fused to the lead network through feature fusion, allowing the lead network to retain rich lower feature information. Finally, the lower feature information in the prediction layer increases. The experimental results show that CBSSD has a significantly higher recognition rate and a lower false detection rate than conventional algorithms, and it still maintains a good detection effect under low illumination. This is of great significance to small object detection using images taken by UAVs in traffic scenes. Furthermore, a method to improve the SSD algorithm is proposed.

show abstract

“…Network Structure. In this study, the SSD model with VGG16 [17,19,20] as the main network was selected.…”

Section: Lead Networkmentioning

confidence: 99%

“…To solve this problem, we propose a composite backbone SSD (CBSSD) object detection method. Based on the CBNet network, we introduce the ResNet50 [16][17][18]…”

Section: Introductionmentioning

confidence: 99%

UAV Image Small Object Detection Based on Composite Backbone Network

Liu

Qiang

et al. 2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…In particular, the ResNet network is the most representative, which deepens the training depth of the network, and alleviates the problems of gradient disappearance or explosion, network degradation, and so on. Many studies have used ResNet to improve the semantic segmentation model and have achieved relatively successful results [27][28][29]. Therefore, this paper chooses to use the ResNet-50 network to fuse FCN, U-net, and DeeplabV3+ models to improve the recognition accuracy of cyanobacteria blooms.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Identification of Cyanobacteria Blooms in Lakeshore Zone Using Camera and Semantic Segmentation: A Case Study of Lake Chaohu (Eastern China)

Wang

Qiu

et al. 2023

Sustainability

View full text Add to dashboard Cite

The surface water in the lakeshore zone is the primary area where cyanobacteria bloom floats intensively. In lake water environment monitoring, it has become pressing to accurately identify the distribution and accumulation coverage area of cyanobacteria blooms in the surface water of the lakeshore zone. This study proposes a real-time and dynamic monitoring technology for cyanobacteria blooms in surface water using a shore-based camera monitoring network. The specific work is as follows: Chaohu Lake, a large eutrophic lake in China, is selected as the research object. The multithreading technology is used to dynamically obtain the hourly video images of 43 cameras around Chaohu Lake. The semantic segmentation method is used to identify the cyanobacteria blooms in the video images, calculate the coverage of cyanobacteria blooms, and draw the spatial distribution map of cyanobacteria blooms in the lakeshore zone of Chaohu Lake. To improve the accuracy of cyanobacteria blooms recognition, we use the ResNet-50 network to integrate three semantic segmentation models, namely FCN, U-net, and DeeplabV3+. By comparing the cyanobacteria blooms results identified by the three methods, it is found that the boundary of the cyanobacteria blooms results identified by DeeplabV3+(ResNet-50) is clear, which is more consistent with the real spatial information of the distribution of cyanobacteria blooms and is more suitable for monitoring the hourly dynamic changes of cyanobacteria blooms in the Chaohu Lake lakeshore zone. The results demonstrated that the time requirement of monitoring cyanobacteria blooms in real time on an hourly basis could be met by utilizing technology that uses multiple threads. The OA (Overall Accuracy), MPA (Mean Pixel Accuracy), IOU (Intersection Over Union) of cyanobacteria blooms, and the IOU of water values of the DeeplabV3+(ResNet-50) were the highest, which were 0.83, 0.82, 0.71, and 0.74, and the RMSE between the predicted and real cyanobacterial blooms coverage of 43 cameras was 6.65%. The above values show that DeeplabV3+(ResNet-50) is this technology’s most suitable semantic segmentation model. This technique can provide technical support for the scientific development of a cyanobacteria blooms management plan in the lakeshore zone of Chaohu Lake by calculating the coverage area of cyanobacteria blooms and drawing the spatial distribution map of cyanobacteria blooms in the lakeshore zone.

show abstract

“…For instance, there are a million parameters defining a deep learning model, which requires large amounts of data to learn from it and is a computationally intensive process. Especially, when the data size and the deep learning models become larger and more complicated, training a model within a considerate period usually demands more hardware memory and computing power such as parallel and distributed computing [2] [3] [4] including data parallelism [5], model parallelism [6], pipeline parallelism [7] and hybrid parallelism [8]. Recently, various distributed deep learning frameworks such as Caffe-MPI [9], TensorFlow [10], MXNet [11], Chainer [12], CNTK [13]) have been proposed, which provide basic building blocks for designing effective neural network models for targeted applications.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Distributed Deep Learning Frameworks in a Multi-GPU Environment

Tulasi

Han

Lloyd

et al. 2021

2021 20th International Conference on Ubiquitous Computing and Communications (IUCC/CIT/DSCI/SmartCNS)

View full text Add to dashboard Cite

Deep Learning frameworks, such as TensorFlow, MXNet, Chainer, provide many basic building blocks for designing effective neural network models for various applications (e.g. computer vision, speech recognition, natural language processing). However, run-time performance of these deep learning frameworks varies significantly even when training identical deep network models on the same GPUs. This study presents an experimental analysis and performance model for assessing deep learning models (Convolutional Neural Networks (CNNs), Multilayer Perceptrons (MLP), Autoencoder) on three frameworks: TensorFlow, MXNet, and Chainer, in a multi-GPU environment. We analyse factors that influence these frameworks' performance by computing the running time of each framework in our proposed model, taking load imbalance factor into account. The evaluation results highlight significiant differences in the scalability of the frameworks, and the importance of load balance in parallel distributed deep learning.

show abstract

Distributed Deep Learning of ResNet50 and VGG16 with Pipeline Parallelism

Cited by 9 publications

References 4 publications

UAV Image Small Object Detection Based on Composite Backbone Network

UAV Image Small Object Detection Based on Composite Backbone Network

Real-Time Identification of Cyanobacteria Blooms in Lakeshore Zone Using Camera and Semantic Segmentation: A Case Study of Lake Chaohu (Eastern China)

Performance Analysis of Distributed Deep Learning Frameworks in a Multi-GPU Environment

Contact Info

Product

Resources

About