Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
About
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.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Object Detection | PASCAL VOC 2007 (test) | mAP63.1 | 821 | |
| Image Classification | ImageNet (test) | -- | 235 | |
| Crowd Counting | ShanghaiTech Part A (test) | MAE59.4 | 227 | |
| Classification | PASCAL VOC 2007 (test) | mAP (%)82.44 | 217 | |
| Image Classification | ImageNet 2012 (val) | -- | 202 | |
| Crowd Counting | ShanghaiTech Part B (test) | MAE6.5 | 191 | |
| Image Classification | Caltech-101 | -- | 146 | |
| Image Classification | VOC 2007 (test) | mAP82.4 | 67 | |
| Object Detection | PASCAL VOC 2007 (test) | mAP63.1 | 59 | |
| Crowd Counting | UCF_CC_50 (5-fold cross-validation) | MAE232.6 | 43 |