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
Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions
TL;DR: Li et al. as discussed by the authors proposed a real-time convolutional neural network for semantic segmentation of full 3D LiDAR point clouds, which can achieve the best accuracy vs. computational complexity trade-off in SemanticKITTI bench-mark and is designed on the basis of a new encoder-decoder architecture with lightweight harmonic dense convolutions as its core.
Book ChapterDOI
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network
TL;DR: This work proposes a light-weight robust fine-tuned neural network-based classifier architecture called Fake Detection Fine-tuning Network (FDFtNet), which is capable of detecting many of the new fake face image generation models, and can be easily combined with existing image classification networks and fine- Tuned on a few datasets.
Journal ArticleDOI
Towards Real-time Cooperative Deep Inference over the Cloud and Edge End Devices
TL;DR: This paper forms the optimal DNN partition as a min-cut problem in a directed acyclic graph (DAG) specially derived from the DNN and proposes a novel two-stage approach named quick deep model partition (QDMP), which enables real-time cooperative deep inference over the cloud and edge end devices.
Proceedings ArticleDOI
Learning Strict Identity Mappings in Deep Residual Networks
TL;DR: S-ResNet as discussed by the authors proposes to automatically discard redundant layers, which produces responses that are smaller than a threshold, without any loss in performance, using a few additional rectified linear units in the original ResNet.
Posted Content
OpenEI: An Open Framework for Edge Intelligence
TL;DR: In this article, an Open Framework for Edge Intelligence (OpenEI) is introduced, which is a lightweight software platform to equip edge computing with intelligent processing and data sharing capability.
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.