Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
524 citations
522 citations
521 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...As illustrated in Figure 2, the architecture of UnitBox is derived from VGG16 model [11], in which we remove the fully connected layers and add two branches of fully convolutional layers to predict the pixel-wise bounding boxes and classification scores, respectively....
[...]
...While the deep convolutional neural networks (CNNs) has witnessed major breakthroughs in visual object recognition [3] [11] [13], the CNN-based object detectors have also achieved the state-of-the-arts results on a wide range of applications, such as face detection [8] [5], pedestrian detection [9] [4] and etc [2] [1] [10]....
[...]
519 citations
Cites background from "Very Deep Convolutional Networks fo..."
...3 – – – University of Oxford Karen Simonyan, Andrew Zisserman (Simonyan and Zisserman 2014) XYZ 11....
[...]
518 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Specifically, VGG [166] used stacked more convolutions with of small kernel size to win the ImageNet large scale visual recognition (LSVR) challenge 2014 via stacked more convolutions with of small kernels....
[...]
...VGG [166] and GoogleNet [173]) were widely applied in fields of image [193, 187], video [124, 112], nature language processing [45] and speech processing [229], especially low-level computer vision [153, 179]....
[...]
...Although VGG and GoogLeNet methods are effective for image applications, they are faced with the following drawbacks: (1) if network is very deep, this network may result in vanishing or exploding gradients....
[...]
...After that, deep network architectures (e.g. VGG [166] and GoogleNet [173]) were widely applied in fields of image [193, 187], video [124, 112], nature language processing [45] and speech processing [229], especially low-level computer vision [153, 179]....
[...]
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations