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
Posted Content
Densely Connected Pyramid Dehazing Network
He Zhang,Vishal M. Patel +1 more
TL;DR: A new end-to-end single image dehazing method, called Densely Connected Pyramid Dehazing Network (DCPDN), which can jointly learn the transmission map, atmospheric light and dehazed all together by directly embedding the atmospheric scattering model into the network.
Posted Content
Relation Networks for Object Detection
TL;DR: An object relation module is proposed that processes a set of objects simultaneously through interaction between their appearance feature and geometry, thus allowing modeling of their relations, which gives rise to the first fully end-to-end object detector.
Proceedings ArticleDOI
MegDet: A Large Mini-Batch Object Detector
TL;DR: In this paper, the authors proposed a large mini-batch object detector (MegDet) to enable the training with a large minibatch size up to 256, so that they can effectively utilize at most 128 GPUs to significantly shorten the training time.
Posted Content
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
TL;DR: In this article, the authors propose to learn a pooling function via combining of max and average pooling, and then combine them in a tree-structured fusion of pooling filters that are themselves learned.
Proceedings Article
Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree
TL;DR: The proposed pooling operations provide a boost in invariance properties relative to conventional pooling and set the state of the art on several widely adopted benchmark datasets; they are also easy to implement, and can be applied within various deep neural network architectures.
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.