Hyperspectral image (HSI) contains both spatial pattern and spectral information which has been widely used in food safety, remote sensing, and medical detection.
More specifically, we scan the whole input images and its priority maps in the form of column vector to obtain a relevance matrix estimating their similarity.
Deep face recognition has achieved remarkable improvements due to the introduction of margin-based softmax loss, in which the prototype stored in the last linear layer represents the center of each class.
This paper focuses on the joint synthesis of constant envelope transmit signal and receive filter aimed at optimizing radar performance in signal-dependent interference and spectrally contested-congested environments.
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval.
Recent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e. g. face recognition, facial landmark localization etc.)
Ranked #1 on Face Alignment on COFW (NME metric)
To obtain the accurate transient states of the big scale natural gas pipeline networks under the bad data and non-zero mean noises conditions, a robust Kalman filter-based dynamic state estimation method is proposed using the linearized gas pipeline transient flow equations in this paper.
A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with personalization.
We study the magnetic fields generation from the cosmological first-order electroweak phase transition.
Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology High Energy Physics - Theory
no code implementations • 2 Feb 2021 • S. A. Wadood, Yiyu Zhou, Jing Yang, Kevin Liang, M. A. Alonso, X. -F. Qian, T. Malhotra, S. M. Hashemi Rafsanjani, Andrew N. Jordan, Robert W. Boyd, A. N. Vamivakas
Analyses based on quantum metrology have shown that the ability to localize the positions of two incoherent point sources can be significantly enhanced through the use of mode sorting.
Optics Quantum Physics
We advocate for a method that optimizes the output feature of the penultimate layer of the student network and hence is directly related to representation learning.
We demonstrate the feasibility of this framework by proposing an approach underpinned by the framework for organizational model discovery, and also conduct experiments on real-life event logs to discover and evaluate organizational models.
With the growth of sensing, control and robotic technologies, autonomous underwater vehicles (AUVs) have become useful assistants to human divers for performing various underwater operations.
3D face reconstruction from a single image is a challenging problem, especially under partial occlusions and extreme poses.
This paper shows how to train binary networks to within a few percent points ($\sim 3-5 \%$) of the full precision counterpart.
To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from the teacher to the student.
The decentralized stochastic multi-player multi-armed bandit (MP-MAB) problem, where the collision information is not available to the players, is studied in this paper.
no code implementations • 20 Feb 2020 • Hanshu Cai, Yiwen Gao, Shuting Sun, Na Li, Fuze Tian, Han Xiao, Jianxiu Li, Zhengwu Yang, Xiaowei Li, Qinglin Zhao, Zhenyu Liu, Zhijun Yao, Minqiang Yang, Hong Peng, Jing Zhu, Xiaowei Zhang, Guoping Gao, Fang Zheng, Rui Li, Zhihua Guo, Rong Ma, Jing Yang, Lan Zhang, Xiping Hu, Yumin Li, Bin Hu
The EEG dataset includes not only data collected using traditional 128-electrodes mounted elastic cap, but also a novel wearable 3-electrode EEG collector for pervasive applications.
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results.
Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements.
Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting.
In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring.
We aim to show that when the user preferences are sufficiently diverse and each arm can be optimal for certain users, the O(log T) regret incurred by exploring the sub-optimal arms under the standard stochastic MAB setting can be reduced to a constant.
Crowd counting, i. e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications.
We propose and analyze a self-adaptive version of the $(1,\lambda)$ evolutionary algorithm in which the current mutation rate is part of the individual and thus also subject to mutation.
Although neural machine translation(NMT) yields promising translation performance, it unfortunately suffers from over- and under-translation is- sues [Tu et al., 2016], of which studies have become research hotspots in NMT.
It has been observed that some working principles of evolutionary algorithms, in particular, the influence of the parameters, cannot be understood from results on the asymptotic order of the runtime, but only from more precise results.
Our objective is to understand how the costs and reward of the actions would affect the optimal behavior of the user in both offline and online settings, and design the corresponding opportunistic spectrum access strategies to maximize the expected cumulative net reward (i. e., reward-minus-cost).
This paper describes our system used for the end-to-end (E2E) natural language generation (NLG) challenge.
Ranked #7 on Data-to-Text Generation on E2E NLG Challenge
We propose a new way to self-adjust the mutation rate in population-based evolutionary algorithms in discrete search spaces.
Recently, the compressive tracking (CT) method has attracted much attention due to its high efficiency, but it cannot well deal with the large scale target appearance variations due to its data-independent random projection matrix that results in less discriminative features.