Rethinking the Inception Architecture for Computer Vision
Christian Szegedy,Vincent Vanhoucke,Sergey Ioffe,Jonathon Shlens,Zbigniew Wojna +4 more
- Vol. 2016, pp 2818-2826
TLDR
In this article, the authors explore ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.Abstract:
Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we are exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21:2% top-1 and 5:6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3:5% top-5 error and 17:3% top-1 error on the validation set and 3:6% top-5 error on the official test set.read more
Citations
More filters
Proceedings ArticleDOI
Densely Connected Convolutional Networks
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Book ChapterDOI
SSD: Single Shot MultiBox Detector
Wei Liu,Dragomir Anguelov,Dumitru Erhan,Christian Szegedy,Scott Reed,Cheng-Yang Fu,Alexander C. Berg +6 more
TL;DR: The approach, named SSD, discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per feature map location, which makes SSD easy to train and straightforward to integrate into systems that require a detection component.
Journal ArticleDOI
Squeeze-and-Excitation Networks
TL;DR: This work proposes a novel architectural unit, which is term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels and finds that SE blocks produce significant performance improvements for existing state-of-the-art deep architectures at minimal additional computational cost.
Posted Content
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Andrew Howard,Menglong Zhu,Bo Chen,Dmitry Kalenichenko,Weijun Wang,Tobias Weyand,M. Andreetto,Hartwig Adam +7 more
TL;DR: This work introduces two simple global hyper-parameters that efficiently trade off between latency and accuracy and demonstrates the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.
Proceedings ArticleDOI
Xception: Deep Learning with Depthwise Separable Convolutions
TL;DR: This work proposes a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions, and shows that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset, and significantly outperforms it on a larger image classification dataset.
References
More filters
Proceedings ArticleDOI
Fully convolutional networks for semantic segmentation
TL;DR: The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.
Proceedings ArticleDOI
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Proceedings ArticleDOI
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
TL;DR: In this paper, a Parametric Rectified Linear Unit (PReLU) was proposed to improve model fitting with nearly zero extra computational cost and little overfitting risk, which achieved a 4.94% top-5 test error on ImageNet 2012 classification dataset.
Proceedings ArticleDOI
FaceNet: A unified embedding for face recognition and clustering
TL;DR: A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Proceedings ArticleDOI
Large-Scale Video Classification with Convolutional Neural Networks
TL;DR: This work studies multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggests a multiresolution, foveated architecture as a promising way of speeding up the training.