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
Proceedings ArticleDOI
ApproxDet: content and contention-aware approximate object detection for mobiles
Ran Xu,Chen-Lin Zhang,Pengcheng Wang,Jayoung Lee,Subrata Mitra,Somali Chaterji,Yin Li,Saurabh Bagchi +7 more
TL;DR: ApproxDet is introduced, an adaptive video object detection framework for mobile devices to meet accuracy-latency requirements in the face of changing content and resource contention scenarios and is able to adapt to a wide variety of contention and content characteristics and outshines all baselines.
Proceedings Article
Winning the Lottery with Continuous Sparsification
TL;DR: Continuous Sparsification is proposed, a new algorithm to search for winning tickets which continuously removes parameters from a network during training, and learns the sub-network's structure with gradient-based methods instead of relying on pruning strategies.
Proceedings ArticleDOI
Learning Monocular Visual Odometry with Dense 3D Mapping from Dense 3D Flow
TL;DR: In this article, a dual-stream L-VO network is used to predict the 6DOF relative pose and furthermore reconstruct the vehicle trajectory by learning the correlation between motion directions.
Posted Content
An Accurate EEGNet-based Motor-Imagery Brain-Computer Interface for Low-Power Edge Computing
TL;DR: This paper presents an accurate and robust embedded motor-imagery brain–computer interface (MI-BCI), based on EEGNet, that matches the requirements of memory footprint and computational resources of low-power microcontroller units (MCUs), such as the ARM Cortex-M family.
Proceedings ArticleDOI
Searching for Fast Model Families on Datacenter Accelerators
TL;DR: Wang et al. as discussed by the authors proposed a DC-accelerator-optimized search space, with space-to-depth, space to-batch, hybrid fused convolution structures with vanilla and depthwise convolutions, and block-wise activation functions.
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.