Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
复制标题
DOI：
10.1109/tpami.2015.2389824
复制
发表时间：
2015-09-01
影响因子：
23.6
通讯作者：
Sun, Jian
中科院分区：
文献类型：
--
作者：
He, Kaiming;Zhang, Xiangyu;Sun, Jian
现有的深度卷积神经网络（CNN）需要固定大小（例如，224 x224）输入图像。该要求是“人为的”，并且可能降低任意尺寸/尺度的图像或子图像的识别准确度。在这项工作中，我们配备了另一种池化策略，“空间金字塔池化”，以消除上述要求的网络。新的网络结构，称为SPP网络，可以生成一个固定长度的表示，而不管图像的大小/规模。金字塔池化对于对象变形也具有鲁棒性。有了这些优点，SPP-网络应该在总体上改进所有基于CNN的图像分类方法。在ImageNet 2012数据集上，我们证明了SPP-net提高了各种CNN架构的准确性，尽管它们的设计不同。在Pascal VOC 2007和Caltech 101数据集上，SPP-net使用单个全图像表示实现了最先进的分类结果，无需微调。SPP网络的强大功能在目标检测中也很重要。使用SPP网络，我们只计算一次整个图像的特征图，然后将任意区域（子图像）中的特征集中起来，以生成固定长度的表示来训练检测器。该方法避免了重复计算卷积特征。在处理测试图像时，我们的方法比R-CNN方法快24- 102倍，同时在Pascal VOC 2007上实现了更好或相当的准确性。在2014年ImageNet大规模视觉识别挑战赛（ILSVRC）中，我们的方法在所有38个团队中的对象检测中排名第2，在图像分类中排名第3。本文还介绍了为本次比赛所做的改进。
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224x224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with another pooling strategy, "spatial pyramid pooling", to eliminate the above requirement. The new network structure, called SPP-net, can generate a fixed-length representation regardless of image size/scale. Pyramid pooling is also robust to object deformations. With these advantages, SPP-net should in general improve all CNN-based image classification methods. On the ImageNet 2012 dataset, we demonstrate that SPP-net boosts the accuracy of a variety of CNN architectures despite their different designs. On the Pascal VOC 2007 and Caltech101 datasets, SPP-net achieves state-of-the-art classification results using a single full-image representation and no fine-tuning. The power of SPP-net is also significant in object detection. 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. This method avoids repeatedly computing the convolutional features. 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. In ImageNet Large Scale Visual Recognition Challenge (ILSVRC) 2014, our methods rank #2 in object detection and #3 in image classification among all 38 teams. This manuscript also introduces the improvement made for this competition.