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
Ristretto: A Framework for Empirical Study of Resource-Efficient Inference in Convolutional Neural Networks
TL;DR: Ristretto is a CNN approximation framework that enables empirical investigation of the tradeoff between various number representation and word width choices and the classification accuracy of the model and is used to demonstrate that three ImageNet networks can be condensed to use 8-bit dynamic fixed point for network weights and activations.
Proceedings Article
Pelee: a real-time object detection system on mobile devices
TL;DR: In this article, the authors proposed an efficient architecture named PeleeNet, which is built with conventional convolution instead and achieves a higher accuracy and over 1.8 times faster speed than MobileNet and MobileNetV2 on NVIDIA TX2.
Proceedings Article
Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM
TL;DR: This paper focuses on compressing and accelerating deep models with network weights represented by very small numbers of bits, referred to as extremely low bit neural network, and proposes to solve this problem using extragradient and iterative quantization algorithms that lead to considerably faster convergency compared to conventional optimization methods.
Proceedings ArticleDOI
Re-Identification With Consistent Attentive Siamese Networks
TL;DR: In this paper, a new attention-driven Siamese learning architecture, called Consistent Attentive siamese Network (CASN), is proposed for person re-ID.
Journal ArticleDOI
Fp-bnn
TL;DR: FP-BNN, a binarized neural network (BNN) for FPGAs, is presented, which drastically cuts down the hardware consumption while maintaining acceptable accuracy, and an inference performance of Tera opartions per second with acceptable accuracy loss is obtained.
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.