Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

18 Jun 2014Kaiming He • Xiangyu Zhang • Shaoqing Ren • Jian Sun

This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. Pyramid pooling is also robust to object deformations. In processing test images, our method is 24-102x faster than the R-CNN method, while achieving better or comparable accuracy on Pascal VOC 2007.

PDF Abstract


Task Dataset Model Metric name Metric value Global rank Compare
Object Detection PASCAL VOC 2007 SPP (Overfeat-7) MAP 82.44% # 4