Open AccessProceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TLDR
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.Abstract:
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) 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. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.read more
Citations
More filters
Posted Content
TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
TL;DR: This paper demonstrates how the U-Net type architecture can be improved by the use of the pre-trained encoder and compares three weight initialization schemes: LeCun uniform, the encoder with weights from VGG11 and full network trained on the Carvana dataset.
Proceedings ArticleDOI
Detecting Visual Relationships with Deep Relational Networks
Bo Dai,Yuqi Zhang,Dahua Lin +2 more
TL;DR: In this paper, the Deep Relational Network (DRN) is proposed to exploit the statistical dependencies between objects and their relationships, which achieves substantial improvement over state-of-the-art methods.
Proceedings Article
Universal Style Transfer via Feature Transforms
TL;DR: In this paper, a pair of feature transforms, whitening and coloring, are embedded to an image reconstruction network to reflect direct matching of feature covariance of the content image to a given style image, which shares similar spirit with the optimization of Gram matrix based cost in neural style transfer.
Journal ArticleDOI
3D deeply supervised network for automated segmentation of volumetric medical images.
TL;DR: The proposed 3D DSN is capable of conducting volume‐to‐volume learning and inference, which can eliminate redundant computations and alleviate the risk of over‐fitting on limited training data, and the3D deep supervision mechanism can effectively cope with the optimization problem of gradients vanishing or exploding when training a 3D deep model.
Journal ArticleDOI
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
TL;DR: A simple approach which consists of two homogeneous branches to predict pixel-wise objectness scores and re-ID features allows \emph{FairMOT} to obtain high levels of detection and tracking accuracy and outperform previous state-of-the-arts by a large margin on several public datasets.
References
More filters
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 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.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).