Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

18 Jun 2014  ·  Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun ·

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.

PDF Abstract

Results from the Paper


 Ranked #1 on Image Classification on ImageNet (Hardware Burden metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification ImageNet SPPNet Top 5 Accuracy 91.86 # 206
Hardware Burden None # 1
Operations per network pass None # 1
Image Classification ImageNet MSRA Top 5 Accuracy 89.05 # 216
Object Detection PASCAL VOC 2007 SPP(combination) MAP 60.9% # 25

Methods