ThinNet: An Efficient Convolutional Neural Network for Object Detection

Cao, Sen; Liu, Yazhou; Zhou, Changxin; Sun, Quansen; Lasang, Pongsak; Shen, Sheng Mei

doi:10.1109/icpr.2018.8545809

Cited by 3 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A typical solution consists to re-design network components to achieve similar results with smaller resources. It is the case of MobileNets [10] and ThinNet [2], where the authors substitute classical convolutions with depthwise separable convolutions. Another example is SqueezeNet [12], achieving the same accuracy of AlexNet with 50 times less parameters.…”

Section: Related Workmentioning

confidence: 99%

A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision

Ressi

Pistellato

Albarelli

et al. 2022

AIxIA 2021 – Advances in Artificial Intelligence

View full text Add to dashboard Cite

A significant amount of Deep Learning research deals with the reduction of network complexity. In most scenarios the preservation of very high performance has priority over size reduction. However, when dealing with embedded systems, the limited amount of resources forces a switch in perspective. In fact, being able to dramatically reduce complexity could be a stronger requisite for overall feasibility than excellent performance. In this paper we propose a simple to implement yet effective method to largely reduce the size of Convolutional Neural Networks with minimal impact on their performance. The key idea is to assess the relevance of each kernel with respect to a representative dataset by computing the output of its activation function and to trim them accordingly. The resulting network becomes small enough to be adopted on embedded hardware, such as smart cameras or lightweight edge processing units. In order to assess the capability of our method with respect to real-world scenarios, we adopted it to shrink two different pre-trained networks to be hosted on general purpose low-end FPGA hardware to be found in embedded cameras. Our experiments demonstrated both the overall feasibility of the method and its superior performance when compared with similar size-reducing techniques introduced in recent literature.

show abstract

Section: Related Workmentioning

confidence: 99%

A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision

Ressi

Pistellato

Albarelli

et al. 2022

AIxIA 2021 – Advances in Artificial Intelligence

View full text Add to dashboard Cite

show abstract

Rethinking of Deep Models Parameters with Respect to Data Distribution

Prasad

Lin

et al. 2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

A novel fuzzy pooling based modified ThinNet architecture for lemon fruit classification

Sundaram

Shankar²,

Reddy³

2022

IFS

View full text Add to dashboard Cite

Computer vision functions like object detection, image segmentation, and image classification were recently getting advance due to Convolutional Neural Networks (CNNs). In the food and agricultural industries, image classification plays a critical role in quality control. CNNs are made up of layers that alternate between convolutional, nonlinearity, and feature pooling. In this article, we proposed Fuzzy Pooling, a novel pooling approach that works based on fuzzy logic, that can increase the accuracy of the CNNs by replacing the conventional pooling layer. This proposed Fuzzy Pooling was put to the test with CIFAR-10 and SVHN data sets on single layer CNN, and it outperformed previous pooling strategies by achieving 92% and 97% classification accuracy. This proposed Fuzzy Pooling layer was replaced the Max Pooling layer in the ThinNet architecture, and it was trained using the back propagation method. It was demonstrated experimentally on the Lemon fruit data set to classify the fruits into three categories such as Good, Medium, and Poor. In order to classify the lemon fruit into three categories, the 1000 Fully Connected layer in ThinNet architecture was replaced with three Fully Connected layers. The Modified ThinNet architecture called ThinNet_FP was trained with a learning rate of 0.001 and achieved 97% accuracy in classifying the images and outperformed previous CNN architectures when trained on the same data set.

show abstract

ThinNet: An Efficient Convolutional Neural Network for Object Detection

Cited by 3 publications

References 13 publications

A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision

A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision

Rethinking of Deep Models Parameters with Respect to Data Distribution

A novel fuzzy pooling based modified ThinNet architecture for lemon fruit classification

Contact Info

Product

Resources

About