Huawei

About: Huawei is a company organization based out in Shenzhen, China. It is known for research contribution in the topics: Terminal (electronics) & Node (networking). The organization has 41417 authors who have published 44698 publications receiving 343496 citations. The organization is also known as: Huawei Technologies & Huawei Technologies Co., Ltd..

Learning to answer questions from image using convolutional neural network

Abstract: In this paper, we propose to employ the convolutional neural network (CNN) for the image question answering (QA) task. Our proposed CNN provides an end-to-end framework with convolutional architectures for learning not only the image and question representations, but also their inter-modal interactions to produce the answer. More specifically, our model consists of three CNNs: one image CNN to encode the image content, one sentence CNN to compose the words of the question, and one multimodal convolution layer to learn their joint representation for the classification in the space of candidate answer words. We demonstrate the efficacy of our proposed model on the DAQUAR and COCO-QA datasets, which are two benchmark datasets for image QA, with the performances significantly outperforming the state-of-the-art.

Pilot Reuse for Massive MIMO Transmission over Spatially Correlated Rayleigh Fading Channels

Abstract: We propose pilot reuse (PR) in single cell for massive multiuser multiple-input multiple-output (MIMO) transmission to reduce the pilot overhead. For spatially correlated Rayleigh fading channels, we establish a relationship between channel spatial correlations and channel power angle spectrum when the base station antenna number tends to infinity. With this channel model, we show that sum mean square error (MSE) of channel estimation can be minimized provided that channel angle of arrival intervals of the user terminals reusing the pilots are non-overlapping, which shows feasibility of PR over spatially correlated massive MIMO channels with constrained channel angular spreads. Since channel estimation performance might degrade due to PR, we also develop the closed-form robust multiuser uplink receiver and downlink precoder that minimize sum MSE of signal detection, and reveal a duality between them. Subsequently, we investigate pilot scheduling, which determines the PR pattern, under two minimum MSE related criteria, and propose a low complexity pilot scheduling algorithm, which relies on the channel statistics only. Simulation results show that the proposed PR scheme provides significant performance gains over the conventional orthogonal training scheme in terms of net spectral efficiency.

Tools and benchmarks for automated log parsing

Abstract: Logs are imperative in the development and maintenance process of many software systems. They record detailed runtime information that allows developers and support engineers to monitor their systems and dissect anomalous behaviors and errors. The increasing scale and complexity of modern software systems, however, make the volume of logs explodes. In many cases, the traditional way of manual log inspection becomes impractical. Many recent studies, as well as industrial tools, resort to powerful text search and machine learning-based analytics solutions. Due to the unstructured nature of logs, a first crucial step is to parse log messages into structured data for subsequent analysis. In recent years, automated log parsing has been widely studied in both academia and industry, producing a series of log parsers by different techniques. To better understand the characteristics of these log parsers, in this paper, we present a comprehensive evaluation study on automated log parsing and further release the tools and benchmarks for easy reuse. More specifically, we evaluate 13 log parsers on a total of 16 log datasets spanning distributed systems, supercomputers, operating systems, mobile systems, server applications, and standalone software. We report the benchmarking results in terms of accuracy, robustness, and efficiency, which are of practical importance when deploying automated log parsing in production. We also share the success stories and lessons learned in an industrial application at Huawei. We believe that our work could serve as the basis and provide valuable guidance to future research and deployment of automated log parsing.

MSE-Based Transceiver Designs for the MIMO Interference Channel

Abstract: Interference alignment (IA) has evolved as a powerful technique in the information theoretic framework for achieving the optimal degrees of freedom of interference channel. In practical systems, the design of specific interference alignment schemes is subject to various criteria and constraints. In this paper, we propose novel transceiver schemes for the MIMO interference channel based on the mean square error (MSE) criterion. Our objective is to optimize the system performance under a given and feasible degree of freedom. Both the total MSE and the maximum per-user MSE are chosen to be the objective functions to minimize. We show that the joint design of transmit precoding matrices and receiving filter matrices with both objectives can be realized through efficient iterative algorithms. The convergence of the proposed algorithms is proven as well. Simulation results show that the proposed schemes outperform the existing IA schemes in terms of BER performance. Considering the imperfection of channel state information (CSI), we also extend the MSE-based transceiver schemes for the MIMO interference channel with CSI estimation error. The robustness of the proposed algorithms is confirmed by simulations.

Attention-Guided Unified Network for Panoptic Segmentation

Abstract: This paper studies panoptic segmentation, a recently proposed task which segments foreground (FG) objects at the instance level as well as background (BG) contents at the semantic level. Existing methods mostly dealt with these two problems separately, but in this paper, we reveal the underlying relationship between them, in particular, FG objects provide complementary cues to assist BG understanding. Our approach, named the Attention-guided Unified Network (AUNet), is a unified framework with two branches for FG and BG segmentation simultaneously. Two sources of attentions are added to the BG branch, namely, RPN and FG segmentation mask to provide object-level and pixel-level attentions, respectively. Our approach is generalized to different backbones with consistent accuracy gain in both FG and BG segmentation, and also sets new state-of-the-arts both in the MS-COCO (46.5% PQ) and Cityscapes (59.0% PQ) benchmarks.