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 Article
Measuring the Intrinsic Dimension of Objective Landscapes.
TL;DR: In this paper, the authors propose to train networks not in their native parameter space, but instead in a smaller, randomly oriented subspace, and define this to be the intrinsic dimension of the objective landscape.
Journal ArticleDOI
Deep learning and transfer learning features for plankton classification
Alessandra Lumini,Loris Nanni +1 more
TL;DR: This work studies both the fine tuning of several deep learned models and transfer learning from the same models with the aim of exploiting their diversity in designing an ensemble of classifiers, and shows how to combine different CNN in order to improve the performance.
Posted Content
Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM
TL;DR: In this paper, the authors focus 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 model this problem as a discretely constrained optimization problem.
Book ChapterDOI
YOLO3D: End-to-End Real-Time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud
TL;DR: The main contribution is in extending the loss function of YOLO v2 to include the yaw angle, the 3D box center in Cartesian coordinates and the height of the box as a direct regression problem, which enables real-time performance, which is essential for automated driving.
Book ChapterDOI
Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks
TL;DR: A saliency-based distortion layer for convolutional neural networks that helps to improve the spatial sampling of input data for a given task and applies to improve existing networks for the tasks of human gaze estimation and fine-grained object classification.
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.