Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
822 citations
Cites background from "Very Deep Convolutional Networks fo..."
...VGG-Net [47] proposes a modular network design strategy, stacking the same type of network blocks repeatedly, which simplifies the workflow of network design and transfer learning for downstream applications....
[...]
821 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...We show that this makes it practical to train deep and efficient networks similar to VGG networks [20] or ResNets [7], and that it is well suited for the task of point-wise semantic segmentation....
[...]
...This rapid growth of the number of active sites is a poor prospect when implementing modern convolutional network architectures that comprise tens or even hundreds of convolutional layers, such as VGG networks, ResNets, or DenseNets [8, 9, 20]....
[...]
815 citations
811 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...4 billion floating point operations (GFLOP) per image, while VGG-16 [25] from ILSVRC 2014 required 552 MB of parameters and 30....
[...]
...• CNV is a convolutional network topology inspired by BinaryNet [5] and VGG-16 [25]....
[...]
...• CNV is a convolutional network topology inspired by BinaryNet [5] and VGG-16 [24]....
[...]
...For instance, AlexNet [14] (the winning entry for ImageNet Large Scale Visual Recognition Competition (ILSVRC) [22] in 2012) required 244 MB of parameters and 1.4 billon floating point operations (GFLOP) per image, while VGG-16 [24] from ILSVRC 2014 required 552MB of parameters and 30.8 GFLOP per image....
[...]
810 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...On the one hand, we build a rich candidate box representation that captures several different aspects of an object such as its pure appearance characteristics, the joint appearance on both sides of the object borders, the distinct appearance of its different regions, context appearance, and…...
[...]
...• We show how to significantly improve the localization capability by coupling the aforementioned CNN recognition model with a CNN model for bounding box regression, adopting a scheme that alternates between scoring candidate boxes and refining their locations, as well as modifying the…...
[...]
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations