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
JPEG-ACT: accelerating deep learning via transform-based lossy compression
TL;DR: This work proposes JPEG for ACTivations (JPEGACT), a lossy activation offload accelerator for training CNNs that works by discarding redundant spatial information, and shows how to optimize the JPEG algorithm so as to ensure convergence and maintain accuracy during training.
Proceedings ArticleDOI
TIMELY: pushing data movements and interfaces in PIM accelerators towards local and in time domain
TL;DR: TIMELY as discussed by the authors adopts analog local buffers (ALBs) within ReRAM crossbars to enhance the data locality, minimizing the energy overheads of both input and partial sum movements.
Journal ArticleDOI
Exploiting Multiple Optimizers with Transfer Learning Techniques for the Identification of COVID-19 Patients.
TL;DR: A robust and efficient method based on transfer learning techniques is proposed to identify normal and COVID-19 patients by employing small training data and is competitive with the available literature, demonstrating that it could be used for the early detection of COVID -19 patients.
Proceedings Article
Vid2Game: Controllable Characters Extracted from Real-World Videos
TL;DR: In this paper, the authors extract a controllable model from a video of a person performing a certain activity, and generate novel image sequences of that person, according to user-defined control signals, typically marking the displacement of the moving body.
Journal ArticleDOI
Evaluation of Object Proposals and ConvNet Features for Landmark-based Visual Place Recognition
Yi Hou,Hong Zhang,Shilin Zhou +2 more
TL;DR: A thorough evaluation of 13 state-of-the-art object proposal methods and 13 kinds of modern ConvNet features on six datasets with various environmental and viewpoint changes, in terms of their place recognition accuracy and computational efficiency is conducted.
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.