Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
780 citations
777 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...With the large success of deep learning in the past years, the object detection community shifted from simple appearance scoring on exhaustive sliding windows [1] to more powerful, multi-layer visual representations [2, 3] extracted from a smaller set of object/region proposals [4, 5]....
[...]
...With the wide success of deep networks [2, 3], which typically operate on a fixed spatial scope, there has been increased interest in object proposal generation....
[...]
...We use OxfordNet [3] trained on ImageNet to initialize the weights of convolutional layers and the branch for candidate boxes....
[...]
772 citations
769 citations
767 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...To facilitate our discussions, we use VGG-16 [13] as our case study....
[...]
...Single scale, without dense evaluation [13]...
[...]
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations