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
Posted Content
Learning Generalisable Omni-Scale Representations for Person Re-Identification
TL;DR: Novel CNN architectures to address person re-identification and cross-dataset discrepancies are developed, including a re-ID CNN termed omni-scale network (OSNet) to learn features that not only capture different spatial scales but also encapsulate a synergistic combination of multiple scales, namely omNI-scale features.
Journal ArticleDOI
Deep learning in multi-object detection and tracking: state of the art
TL;DR: In this article, the authors provide a comprehensive overview of object detection and tracking using deep learning (DL) networks and compare the performance of different object detectors and trackers, including the recent development in granulated DL models.
Journal ArticleDOI
Deep photovoltaic nowcasting
TL;DR: In this article, a multi-layer perceptron (MLP), a convolutional neural network (CNN), and a long short-term memory (LSTM) module were used to predict the future photovoltaic power output.
Journal Article
Testing Robustness Against Unforeseen Adversaries
TL;DR: This work introduces a total of four novel adversarial attacks to create ImageNet-UA's diverse attack suite, and demonstrates that, in comparison to Image net-UA, prevailing L_inf robustness assessments give a narrow account of model robustness.
Proceedings ArticleDOI
Everything You Wanted to Know about Deep Learning for Computer Vision but Were Afraid to Ask
Moacir Antonelli Ponti,Leonardo Sampaio Ferraz Ribeiro,Tiago S. Nazaré,Tu Bui,John Collomosse +4 more
TL;DR: The most fundamental concepts of Deep Learning for Computer Vision in particular CNNs, AEs and GANs are introduced, including architectures, inner workings and optimization.
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.