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 Article
Proposal Flow
TL;DR: In this paper, the authors introduce a novel approach to semantic flow, dubbed proposal flow, that establishes reliable correspondences using object proposals, which can take advantage of both local and geometric consistency constraints among proposals.
Proceedings ArticleDOI
Generative Adversarial Learning Towards Fast Weakly Supervised Detection
TL;DR: This paper proposes a novel generative adversarial learning paradigm for weakly supervised object detection that outperforms all existing schemes in terms of detection accuracy and adapts a structural similarity loss in combination with an adversarial loss into the training objective, which solves the challenge that the bounding boxes produced by the surrogator may not well capture their ground truth.
Journal ArticleDOI
Robust Convolutional Neural Networks for Image Recognition
TL;DR: A new CNN architecture is proposed which achieves state-of-the-art classification results on the different challenge benchmarks and outperform and achieve superior results comparing to the most contemporary approaches.
Journal ArticleDOI
JointRCNN: A Region-Based Convolutional Neural Network for Optic Disc and Cup Segmentation
TL;DR: The proposed JointRCNN model outperforms state-of-the-art methods for optic disc and cup segmentation task and glaucoma detection task and is promising to be used for glAUcoma screening.
Posted Content
Convolution in Convolution for Network in Network
TL;DR: The proposed method is called convolution in convolution (CiC), and one or more layers of the sparse shallow MLP are sparely connected in the channel dimension or channel–spatial domain, and the experimental results demonstrate the effectiveness of the proposed CiC method.
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.