SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size
- Forrest N. Iandola, M. Moskewicz, Khalid Ashraf, Song Han, W. Dally, K. Keutzer
- Computer ScienceArXiv
- 24 February 2016
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).
From captions to visual concepts and back
- Hao Fang, Saurabh Gupta, G. Zweig
- Computer ScienceComputer Vision and Pattern Recognition
- 18 November 2014
This paper uses multiple instance learning to train visual detectors for words that commonly occur in captions, including many different parts of speech such as nouns, verbs, and adjectives, and develops a maximum-entropy language model.
DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
- Forrest N. Iandola, M. Moskewicz, Sergey Karayev, Ross B. Girshick, Trevor Darrell, K. Keutzer
- Computer ScienceArXiv
- 7 April 2014
DenseNet is presented, an open source system that computes dense, multiscale features from the convolutional layers of a CNN based object classifier.
- LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE
- Forrest N. Iandola, Song Han, M. Moskewicz, Khalid Ashraf, W. Dally, K. Keutzer
- Computer Science
- 2016
A small CNN architecture called SqueezeNet is proposed, which achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters and is able to compress to less than 0.5MB (510× smaller than AlexNet).
SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving
- Bichen Wu, Forrest N. Iandola, Peter H. Jin, K. Keutzer
- Computer ScienceIEEE Conference on Computer Vision and Pattern…
- 4 December 2016
SqueezeDet is a fully convolutional neural network for object detection that aims to simultaneously satisfy all of the above constraints, and is very accurate, achieving state-of-the-art accuracy on the KITTI benchmark.
Deformable part models are convolutional neural networks
- Ross B. Girshick, Forrest N. Iandola, Trevor Darrell, Jitendra Malik
- Computer ScienceComputer Vision and Pattern Recognition
- 18 September 2014
This paper shows that a DPM can be formulated as a CNN, thus providing a synthesis of the two ideas and calls the resulting model a DeepPyramid DPM, which is found to significantly outperform DPMs based on histograms of oriented gradients features (HOG) and slightly outperforms a comparable version of the recently introduced R-CNN detection system, while running significantly faster.
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters
- Forrest N. Iandola, M. Moskewicz, Khalid Ashraf, K. Keutzer
- Computer ScienceComputer Vision and Pattern Recognition
- 31 October 2015
FireCaffe is presented, which successfully scales deep neural network training across a cluster of GPUs, and finds that reduction trees are more efficient and scalable than the traditional parameter server approach.
Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction
- Ning Zhang, Ryan Farrell, Forrest N. Iandola, Trevor Darrell
- Computer ScienceIEEE International Conference on Computer Vision
- 1 December 2013
This paper proposes two pose-normalized descriptors based on computationally-efficient deformable part models based on strongly-supervised DPM parts, which enable pooling across pose and viewpoint, in turn facilitating tasks such as fine-grained recognition and attribute prediction.
How to scale distributed deep learning?
- Peter H. Jin, Qiaochu Yuan, Forrest N. Iandola, K. Keutzer
- Computer ScienceArXiv
- 14 November 2016
It is found, perhaps counterintuitively, that asynchronous SGD, including both elastic averaging and gossiping, converges faster at fewer nodes, whereas synchronous SGD scales better to more nodes (up to about 100 nodes).
DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer
- Forrest N. Iandola, Anting Shen, Peter Gao, K. Keutzer
- Computer ScienceArXiv
- 7 October 2015
This work proposes several DCNN architectures, several of which surpass published state-of-art accuracy on a popular logo recognition dataset and applies DCNNs to logo recognition.
...
...