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
Deep Semantic Segmentation and Multi-Class Skin Lesion Classification Based on Convolutional Neural Network
Muhammad Almas Anjum,Javaria Amin,Muhammad Sharif,Habib Ullah Khan,Muhammad Sheraz Arshad Malik,Seifedine Kadry +5 more
TL;DR: The proposed method accurately localized, segmented and classified the skin lesion at an early stage and is evaluated on the top MICCAI ISIC challenging 2017, 2018 and 2019 datasets.
Journal ArticleDOI
Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data
TL;DR: A new Lightness-Guided Shadow Removal Network (LG-ShadowNet) is presented, which first train a CNN module to compensate for the lightness and then train a second CNN module with the guidance of lightness information from the first CNN module for final shadow removal.
Proceedings ArticleDOI
A Systematic Assessment of Embedded Neural Networks for Object Detection
Micaela Verucchi,Gianluca Brilli,Davide Sapienza,Mattia Verasani,Marco Arena,Francesco Gatti,Alessandro Capotondi,Roberto Cavicchioli,Marko Bertogna,Marco Solieri +9 more
TL;DR: A comprehensive and fair comparison of the best-in-class Convolution Neural Networks (CNNs) for real-time embedded systems, detailing the effort made to achieve an unbiased characterization on cutting-edge system-on-chips.
Posted Content
Crack-pot: Autonomous Road Crack and Pothole Detection
TL;DR: In this article, the authors proposed a robust real-time road crack and pothole detection algorithm which can be deployed on any GPU-based conventional processing boards with an associated camera.
Journal ArticleDOI
Block Proposal Neural Architecture Search
TL;DR: This work proposes a new evolutionary algorithm referred to as latency EvoNAS (LEvoNAS) for block structure search, and incorporates it to the NAS framework by developing a novel two-stage framework referred toas Block Proposal NAS (BP-NAS).
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.