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
Detail-Preserving Pooling in Deep Networks
TL;DR: In this article, an adaptive pooling method that magnifies spatial changes and preserves important structural detail is proposed, which can be learned jointly with the rest of the network and consistently outperforms previous pooling approaches.
Posted Content
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization
Spyros Gidaris,Nikos Komodakis +1 more
TL;DR: AttractioNet as discussed by the authors proposes an active strategy for generating box proposals that starts from a set of seed boxes, which are uniformly distributed on the image, and then progressively moves its attention on the promising image areas where it is more likely to discover well localized bounding box proposals.
Journal ArticleDOI
Multi-Scale Residual Convolutional Neural Network for Haze Removal of Remote Sensing Images
Hou Jiang,Ning Lu +1 more
TL;DR: Quantitative analysis proves that the dehazed results of MRCNN are superior to the traditional methods and other networks, and a comparison to haze-free data illustrates the spectral consistency after haze removal and reveals the changes in the vegetation index.
Journal ArticleDOI
Towards Ghost-Free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
TL;DR: A shadow matting generative adversarial network (SMGAN) is designed to synthesize realistic shadow mattings from a given shadow mask and shadow-free image to outperforms other state-of-the-art methods by a large margin.
Posted Content
Convolutional Neural Networks at Constrained Time Cost
Kaiming He,Jian Sun +1 more
TL;DR: In this article, the authors investigate the accuracy of CNNs under constrained time cost and propose a series of controlled comparisons to progressively modify a baseline model while preserving its time complexity, achieving very competitive accuracy in the ImageNet dataset.
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.