scispace - formally typeset
Search or ask a question
Topic

Metric (mathematics)

About: Metric (mathematics) is a research topic. Over the lifetime, 42617 publications have been published within this topic receiving 836571 citations. The topic is also known as: distance function & metric.


Papers
More filters
Book ChapterDOI
08 Oct 2016
Abstract: Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)’s capability of feature extraction. However, the distribution is unknown, so it is difficult to use the geodesic distance when comparing two samples. In practice, the current deep embedding methods use the Euclidean distance for the training and test. On the other hand, the manifold learning methods suggest to use the Euclidean distance in the local range, combining with the graphical relationship between samples, for approximating the geodesic distance. From this point of view, selecting suitable positive (i.e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations. In this paper, we propose a novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation. In addition, we improve the learning by a metric weight constraint, so that the learned metric has a better generalization ability. Experiments show that these two strategies are effective in learning robust deep metrics for person re-identification, and accordingly our deep model significantly outperforms the state-of-the-art methods on several benchmarks of person re-identification. Therefore, the study presented in this paper may be useful in inspiring new designs of deep models for person re-identification.

232 citations

Posted Content
TL;DR: In this article, a region-based neural network is trained to directly infer the correspondence from observed pixels to the shared object representation (NOCS) along with other object information such as class label and instance mask.
Abstract: The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level" 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)---a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

232 citations

Journal ArticleDOI
TL;DR: In this article, the rendezvous value of the region is defined as the probability that two players can find each other in the least expected time, and it is shown how symmetries in the search region may hinder the process by preventing coordination based on concepts such as north or clockwise.
Abstract: The author considers the problem faced by two people who are placed randomly in a known search region and move about at unit speed to find each other in the least expected time. This time is called the rendezvous value of the region. It is shown how symmetries in the search region may hinder the process by preventing coordination based on concepts such as north or clockwise. A general formulation of the rendezvous search problem is given for a compact metric space endowed with a group of isometrics which represents the spatial uncertainties of the players. These concepts are illustrated by considering upper bounds for various rendezvous values for the circle and an arbitrary metric network. The discrete rendezvous problem on a cycle graph for players restricted to symmetric Markovian strategies is then solved. Finally, the author considers the problem faced by two people on an infinite line who each know the distribution of the distance but not the direction to each other.

232 citations

Journal ArticleDOI
TL;DR: In this article, the effects of imperfect estimation of the channel parameters on error probability when known pilot symbols are transmitted among information data were examined under the assumption of a frequency-flat slow Rayleigh fading channel with multiple transmit and receive antennas.
Abstract: Under the assumption of a frequency-flat slow Rayleigh fading channel with multiple transmit and receive antennas, we examine the effects of imperfect estimation of the channel parameters on error probability when known pilot symbols are transmitted among information data. Three different receivers are considered. The first one derives an estimate of the channel [by using either a maximum-likelihood (ML) or a minimum mean square error (MMSE) criterion], and then uses this estimate in the same metric that would be applied if the channel were perfectly known. The second receiver derives again an estimate of the channel, but uses the ML metric conditioned on the channel estimate. Our last receiver simultaneously processes the pilot and data symbols received. Simulation results are exhibited, showing that only a relatively small percentage of the transmitted frame need be allocated to pilot symbols in order to experience an acceptable degradation of error probability due to imperfect channel knowledge. Algorithms for the recursive calculation of the decision metric of the last two receivers are also developed for application to sequential decoding of trellis space-time codes.

232 citations

Journal ArticleDOI
TL;DR: It is demonstrated that the Poisson models reconstruct better structures than all MDS-based methods, particularly at low coverage and high resolution, and the importance of optimizing the transfer function is highlighted.
Abstract: Recent technological advances allow the measurement, in a single Hi-C experiment, of the frequencies of physical contacts among pairs of genomic loci at a genome-wide scale. The next challenge is to infer, from the resulting DNA-DNA contact maps, accurate three dimensional models of how chromosomes fold and fit into the nucleus. Many existing inference methods rely upon \emph{multidimensional scaling} (MDS), in which the pairwise distances of the inferred model are optimized to resemble pairwise distances derived directly from the contact counts. These approaches, however, often optimize a heuristic objective function and require strong assumptions about the biophysics of DNA to transform interaction frequencies to spatial distance, thereby leading to incorrect structure reconstruction. We propose a novel approach to infer a consensus three-dimensional structure of a genome from Hi-C data. The method incorporates a statistical model of the contact counts, assuming that the counts between two loci follow a Poisson distribution whose intensity decreases with the physical distances between the loci. The method can automatically adjust the transfer function relating the spatial distance to the Poisson intensity and infer a genome structure that best explains the observed data. We compare two variants of our Poisson method, with or without optimization of the transfer function, to four different MDS-based algorithms---two metric MDS methods using different stress functions, a nonmetric version of MDS, and ChromSDE, a recently described, advanced MDS method---on a wide range of simulated datasets. We demonstrate that the Poisson models reconstruct better structures than all MDS-based methods, particularly at low coverage and high resolution, and we highlight the importance of optimizing the transfer function. On publicly available Hi-C data from mouse embryonic stem cells, we show that the Poisson methods lead to more reproducible structures than MDS-based methods when we use data generated using different restriction enzymes, and when we reconstruct structures at different resolutions.

231 citations


Network Information
Related Topics (5)
Cluster analysis
146.5K papers, 2.9M citations
83% related
Optimization problem
96.4K papers, 2.1M citations
83% related
Fuzzy logic
151.2K papers, 2.3M citations
83% related
Robustness (computer science)
94.7K papers, 1.6M citations
83% related
Support vector machine
73.6K papers, 1.7M citations
82% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202253
20213,191
20203,141
20192,843
20182,731
20172,341