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 published on a yearly basis
Papers
More filters
TL;DR: In this article, a new quantitative metric called the ratio of spatial frequency error (rSFe) is proposed to objectively evaluate the quality of fused imagery, where the measured value of the proposed metric is used as feedback to a fusion algorithm such that the image quality of the fused image can potentially be improved.
224 citations
TL;DR: It is important to understand both what a classification metric expresses and what it hides.
Abstract: It is important to understand both what a classification metric expresses and what it hides.
224 citations
Patent•
20 Jun 2003TL;DR: In this paper, a set of rates for each data stream to be transmitted in a multi-channel communication system is determined based on the metric associated with the data stream. But the rate for each stream is determined only for the case when the SNR required to support the data rate by the equivalent system is less than or equal to the metric.
Abstract: Techniques to determine a set of rates for a set of data streams to be transmitted in a multi-channel communication system A group of transmission channels to be used for each data stream is initially identified An equivalent system for each group is then defined to have an AWGN (or flat) channel and a spectral efficiency equal to the average spectral efficiency of the transmission channels in the group (216) A metric for each group is then derived based on the associated equivalent system, eg, set to the SNR needed by the equivalent system to support the average spectral efficiency (218) A rate for each data stream is then determined based on the metric associated with the data stream The rate is deemed to be supported by the communication system if the SNR required to support the data rate by the communication system is less than or equal to the metric (226)
223 citations
Posted Content•
TL;DR: A deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification and an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into this architecture, which is beneficial to deep nets.
Abstract: In this paper, we propose a deep end-to-end neu- ral network to simultaneously learn high-level features and a corresponding similarity metric for person re-identification. The network takes a pair of raw RGB images as input, and outputs a similarity value indicating whether the two input images depict the same person. A layer of computing neighborhood range differences across two input images is employed to capture local relationship between patches. This operation is to seek a robust feature from input images. By increasing the depth to 10 weight layers and using very small (3$\times$3) convolution filters, our architecture achieves a remarkable improvement on the prior-art configurations. Meanwhile, an adaptive Root- Mean-Square (RMSProp) gradient decent algorithm is integrated into our architecture, which is beneficial to deep nets. Our method consistently outperforms state-of-the-art on two large datasets (CUHK03 and Market-1501), and a medium-sized data set (CUHK01).
223 citations
13 Dec 2010
TL;DR: A novel method of mapping hashes to short bit-strings, apply it to Weighted Minhash, and achieve more accurate distance estimates from sketches than existing methods, as long as the inputs are sufficiently distinct.
Abstract: We propose a new Consistent Weighted Sampling method, where the probability of drawing identical samples for a pair of inputs is equal to their Jaccard similarity. Our method takes deterministic constant time per non-zero weight, improving on the best previous approach which takes expected constant time. The samples can be used as Weighted Minhash for efficient retrieval and compression (sketching) under Jaccard or L1 metric. A method is presented for using simple data statistics to reduce the running time of hash computation by two orders of magnitude. We compare our method with the random projection method and show that it has better characteristics for retrieval under L1. We present a novel method of mapping hashes to short bit-strings, apply it to Weighted Minhash, and achieve more accurate distance estimates from sketches than existing methods, as long as the inputs are sufficiently distinct. We show how to choose the optimal number of bits per hash for sketching, and demonstrate experimental results which agree with the theoretical analysis.
223 citations