Forrest N. Iandola

Sort by:

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size

Forrest N. Iandola, Matthew W. Moskewicz, Khalid Ashraf, Song Han, William J. Dally, Kurt Keutzer
ArXiv
2017

Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, is typically possible to identify multiple DNN architectures that achieve that… (More)

- LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE

Recent research on deep convolutional neural networks (CNNs) has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple CNN architectures… (More)

From captions to visual concepts and back

Hao Fang, Saurabh Gupta, +9 authors Geoffrey Zweig
2015 IEEE Conference on Computer Vision and…
2015

This paper presents a novel approach for automatically generating image descriptions: visual detectors, language models, and multimodal similarity models learnt directly from a dataset of image… (More)

Deformable part models are convolutional neural networks

Ross B. Girshick, Forrest N. Iandola, Trevor Darrell, Jitendra Malik
2015 IEEE Conference on Computer Vision and…
2015

Deformable part models (DPMs) and convolutional neural networks (CNNs) are two widely used tools for visual recognition. They are typically viewed as distinct approaches: DPMs are graphical models… (More)

FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters

Forrest N. Iandola, Khalid Ashraf, Matthew W. Moskewicz, Kurt Keutzer
2016 IEEE Conference on Computer Vision and…
2016

Long training times for high-accuracy deep neural networks (DNNs) impede research into new DNN architectures and slow the development of high-accuracy DNNs. In this paper we present FireCaffe, which… (More)

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, Kurt Keutzer
2017 IEEE Conference on Computer Vision and…
2017

Object detection is a crucial task for autonomous driving. In addition to requiring high accuracy to ensure safety, object detection for autonomous driving also requires realtime inference speed to… (More)

Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction

Ning Zhang, Ryan Farrell, Forrest N. Iandola, Trevor Darrell
2013 IEEE International Conference on Computer…
2013

Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized, leading traditional… (More)

DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

Forrest N. Iandola, Matthew W. Moskewicz, Sergey Karayev, Ross B. Girshick, Trevor Darrell, Kurt Keutzer
ArXiv
2014

Convolutional Neural Networks (CNNs) can provide accurate object classification. They can be extended to perform object detection by iterating over dense or selected proposed object regions. However,… (More)

DeepLogo: Hitting Logo Recognition with the Deep Neural Network Hammer

Forrest N. Iandola, Anting Shen, Peter Gao, Kurt Keutzer
ArXiv
2015

Recently, there has been a flurry of industrial activity around logo recognition, such as Ditto’s service for marketers to track their brands in user-generated images, and LogoGrab’s mobile app… (More)

How to scale distributed deep learning?

Peter H. Jin, Qiaochu Yuan, Forrest N. Iandola, Kurt Keutzer
ArXiv
2016

Training time on large datasets for deep neural networks is the principal workflow bottleneck in a number of important applications of deep learning, such as object classification and detection in… (More)

Filter Results:

Publication Year

Publication Type

Co-author

Journals and Conferences