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 ContentDOI
Improving Coronavirus (COVID-19) Diagnosis using Deep Transfer Learning
TL;DR: Pre-trained deep learning models develop in this study could be used early screening of coronavirus, however it calls for extensive need to CT or X-rays dataset to develop a reliable application.
Journal ArticleDOI
PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning
TL;DR: This paper introduces a novel pruning method named Drop-path to reduce model parameters of 2D deep CNNs for the first time based on the generalization error boundary, and observes that the convolutional kernels themselves become sparse, rather than some being removed directly.
Journal ArticleDOI
Adaptively Learning Facial Expression Representation via C-F Labels and Distillation
TL;DR: Wang et al. as mentioned in this paper proposed an adaptive supervised objective named AdaReg loss, reweighting category importance coefficients to address the class imbalance and increasing the discrimination power of expression representations.
Posted Content
Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds
Martin Simon,Karl Amende,Andrea Kraus,Jens Honer,Timo Sämann,Hauke Kaulbersch,Stefan Milz,Horst-Michael Gross +7 more
TL;DR: Li et al. as discussed by the authors proposed a novel fusion of neural network based state-of-the-art 3D detector and visual semantic segmentation in the context of autonomous driving, which achieved same results as state of the art in all related categories, while maintaining the performance and accuracy trade-off.
Journal ArticleDOI
Recent advances in surface defect inspection of industrial products using deep learning techniques
TL;DR: The state-of-the-art in surface defect inspection using deep learning is presented and information on publicly available datasets containing surface image samples is provided to facilitate the research on deep learning-based surface inspection.
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.