Patent
Spatial pyramid pooling networks for image processing
TLDR
Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels, and aggregate local features in the divisions.Abstract:
Spatial pyramid pooling (SPP) layers are combined with convolutional layers and partition an input image into divisions from finer to coarser levels, and aggregate local features in the divisions. A fixed-length output may be generated by the SPP layer(s) regardless of the input size. The multi-level spatial bins used by the SPP layer(s) may provide robustness to object deformations. An SPP layer based system may pool features extracted at variable scales due to the flexibility of input scales making it possible to generate a full-image representation for testing. Moreover, SPP networks may enable feeding of images with varying sizes or scales during training, which may increase scale-invariance and reduce the risk of over-fitting.read more
Citations
More filters
Patent
Deeply learned convolutional neural networks (CNNS) for object localization and classification
TL;DR: In this paper, a Region Of Interest (ROI) Pooling layer is used to select regions to be processed by the set of fully connected layers, which uses the response of the multiple convolutional layers of the network to determine the regions where the objects (of different scales) could be located.
Patent
Method and system for vascular disease detection using recurrent neural networks
TL;DR: In this article, a plurality of 2D cross-section image patches are extracted from a 3D computed tomography angiography (CTA) image, each extracted at a respective sampling point along a vessel centerline of a vessel of interest in the 3D CTA image.
Patent
Automated image searching, exploration and discovery
TL;DR: In this paper, a method for processing image data using a computer system is described, which includes: receiving a plurality of image descriptors, each image descriptor representing a unique visual characteristic.
Patent
Deep learning system for cuboid detection
TL;DR: In this article, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images, which can include a plurality of convolutional and non-convolutional layers of a trained convolution neural network.
Patent
Augmented reality display device with deep learning sensors
TL;DR: In this article, a hydra neural network is used to determine an event of a plurality of events using the different types of sensor data from a head-mounted augmented reality (AR) device.
References
More filters
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.
Journal ArticleDOI
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Related Papers (5)
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more