Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Citations
123,388 citations
55,235 citations
44,703 citations
Cites background from "Spatial Pyramid Pooling in Deep Con..."
...Many other nontrivial visual recognition tasks [8, 12, 7, 32, 27] have also...
[...]
30,811 citations
28,225 citations
Cites background from "Spatial Pyramid Pooling in Deep Con..."
...[19] discard the nonconvolutional portion of classification nets to make a feature extractor....
[...]
...These include advances in bounding box object detection [32, 12, 19], part and keypoint prediction [42, 26], and local correspondence [26, 10]....
[...]
References
73,978 citations
49,914 citations
49,639 citations
"Spatial Pyramid Pooling in Deep Con..." refers methods in this paper
...Using SPP-net, we compute the feature maps from the entire image only once, and then pool features in arbitrary regions (sub-images) to generate fixed-length representations for training the detectors....
[...]
46,906 citations
40,826 citations
"Spatial Pyramid Pooling in Deep Con..." refers methods in this paper
...But in practice the GPU implementations (such as cuda-convnet [3] and Caffe [35]) are preferably run on fixed input images....
[...]