Open AccessPosted Content
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Reads0
Chats0
TLDR
This work proposes a small DNN architecture called SqueezeNet, which achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters and is able to compress to less than 0.5MB (510x smaller than AlexNet).Abstract:
Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet).
The SqueezeNet architecture is available for download here: this https URLread more
Citations
More filters
Journal ArticleDOI
Mini-YOLOv3: Real-Time Object Detector for Embedded Applications
TL;DR: A lightweight network with a parameter size of only 16 percent of darknet-53 is constructed and a Multi-Scale Feature Pyramid Network is added based on a simple U-shaped structure to improve the performance of multi-scale object detection, called Mini-YOLOv3.
Proceedings ArticleDOI
A method to estimate the energy consumption of deep neural networks
TL;DR: This work proposes an energy estimation methodology that can estimate the energy consumption of a DNN based on its architecture, sparsity, and bitwidth and believes that this method will play a critical role in bridging the gap between algorithm and hardware design and provide useful insights for the development of energy-efficient DNNs.
Proceedings ArticleDOI
Frequency Domain Acceleration of Convolutional Neural Networks on CPU-FPGA Shared Memory System
Chi Zhang,Viktor K. Prasanna +1 more
TL;DR: A novel mechanism to accelerate state-of-art Convolutional Neural Networks (CNNs) on CPU-FPGA platform with coherent shared memory and exploits the data parallelism of OaA-based 2D convolver and task parallelism to scale the overall system performance.
Journal ArticleDOI
Strengths and weaknesses of deep learning models for face recognition against image degradations
TL;DR: In this paper, the authors investigate the influence of covariates related to image quality and model characteristics, and analyse their impact on the face verification performance of different deep CNN models using the Labelled Faces in the Wild dataset.
Journal ArticleDOI
Plant disease and pest detection using deep learning-based features
Muammer Türkoğlu,Davut Hanbay +1 more
TL;DR: The evaluation results show that deep feature extraction and SVM/ELM classification produced better results than transfer learning, and the fc6 layers of the AlexNet, VGG16, and VGG19 models produced better accuracy scores when compared to the other layers.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.