Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- pp 346-361
TLDR
This work equips the networks with another pooling strategy, “spatial pyramid pooling”, to eliminate the above requirement, and develops a new network structure, called SPP-net, which can generate a fixed-length representation regardless of image size/scale.Abstract:
Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g. 224×224) input image. This requirement is “artificial” and may hurt the recognition accuracy for the images or sub-images of an arbitrary size/scale. In this work, we equip the networks with a more principled 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. By removing the fixed-size limitation, we can improve all CNN-based image classification methods in general. Our SPP-net achieves state-of-the-art accuracy on the datasets of ImageNet 2012, Pascal VOC 2007, and Caltech101.read more
Citations
More filters
Proceedings ArticleDOI
Multi-patch deep features for power line insulator status classification from aerial images
TL;DR: A CNN model with multi-patch feature extraction method is applied to represent the status of insulators and a Support Vector Machine (SVM) is trained based on these features.
Proceedings ArticleDOI
CADP: A Novel Dataset for CCTV Traffic Camera based Accident Analysis
TL;DR: A novel dataset for traffic accidents analysis is presented to resolve the lack of public data for research about automatic spatio-temporal annotations for traffic safety in the roads and to integrate contextual information into conventional Faster R-CNN using Context Mining and Augmented Context Mining to complement the accuracy for small pedestrian detection.
Book ChapterDOI
Quantization Mimic: Towards Very Tiny CNN for Object Detection
TL;DR: In this paper, the authors proposed Quantization Mimic, which first quantizes the large network, then mimics a quantized small network to better match the feature maps from teacher network.
Posted Content
Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond
TL;DR: The proposed framework is built on the Generative Adversarial Network with multiple discriminators, trying to synthesize realistic pedestrians and learn the background context simultaneously, and can smoothly synthesize pedestrians on background images of variations and different levels of details.
Proceedings ArticleDOI
Sparse projections for high-dimensional binary codes
TL;DR: Experiments show that the sparsity encouraging regularizer introduced in this paper leads to better accuracy than dense projections, and is more accurate and faster than other recently proposed methods for speeding up high-dimensional binary encoding.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Journal ArticleDOI
LIBSVM: A library for support vector machines
Chih-Chung Chang,Chih-Jen Lin +1 more
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.