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..

A Fourier-based Framework for Domain Generalization

Abstract: Modern deep neural networks suffer from performance degradation when evaluated on testing data under different distributions from training data. Domain generalization aims at tackling this problem by learning transferable knowledge from multiple source domains in order to generalize to unseen target domains. This paper introduces a novel Fourier-based perspective for domain generalization. The main assumption is that the Fourier phase information contains high-level semantics and is not easily affected by domain shifts. To force the model to capture phase information, we develop a novel Fourier-based data augmentation strategy called amplitude mix which linearly interpolates between the amplitude spectrums of two images. A dual-formed consistency loss called co-teacher regularization is further introduced between the predictions induced from original and augmented images. Extensive experiments on three benchmarks have demonstrated that the proposed method is able to achieve state-of-the-arts performance for domain generalization.

Energy Efficient Multi-User MISO Communication using Low Resolution Large Intelligent Surfaces

Abstract: We consider a multi-user Multiple-Input Single-Output (MISO) communication system comprising of a multi-antenna base station communicating in the downlink simultaneously with multiple single-antenna mobile users. This communication is assumed to be assisted by a Large Intelligent Surface (LIS) that consists of many nearly passive antenna elements, whose parameters can be tuned according to desired objectives. The latest design advances on these surfaces suggest cheap elements effectively acting as low resolution (even $1$-bit resolution) phase shifters, whose joint configuration affects the electromagnetic behavior of the wireless propagation channel. In this paper, we investigate the suitability of LIS for green communications in terms of Energy Efficiency (EE), which is expressed as the number of bits per Joule. In particular, for the considered multi-user MISO system, we design the transmit powers per user and the values for the surface elements that jointly maximize the system's EE performance. Our representative simulation results show that LIS-assisted communication, even with nearly passive $1$-bit resolution antenna elements, provides significant EE gains compared to conventional relay-assisted communication.

PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search

Abstract: Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-net and searching for an optimal architecture. In this paper, we present a novel approach, namely Partially-Connected DARTS, by sampling a small part of super-net to reduce the redundancy in exploring the network space, thereby performing a more efficient search without comprising the performance. In particular, we perform operation search in a subset of channels while bypassing the held out part in a shortcut. This strategy may suffer from an undesired inconsistency on selecting the edges of super-net caused by sampling different channels. We solve it by introducing edge normalization, which adds a new set of edge-level hyper-parameters to reduce uncertainty in search. Thanks to the reduced memory cost, PC-DARTS can be trained with a larger batch size and, consequently, enjoy both faster speed and higher training stability. Experiment results demonstrate the effectiveness of the proposed method. Specifically, we achieve an error rate of 2.57% on CIFAR10 within merely 0.1 GPU-days for architecture search, and a state-of-the-art top-1 error rate of 24.2% on ImageNet (under the mobile setting) within 3.8 GPU-days for search. Our code has been made available at https://www.dropbox.com/sh/on9lg3rpx1r6dkf/AABG5mt0sMHjnEJyoRnLEYW4a?dl=0.

Pose-Guided Photorealistic Face Rotation

Abstract: Face rotation provides an effective and cheap way for data augmentation and representation learning of face recognition. It is a challenging generative learning problem due to the large pose discrepancy between two face images. This work focuses on flexible face rotation of arbitrary head poses, including extreme profile views. We propose a novel Couple-Agent Pose-Guided Generative Adversarial Network (CAPG-GAN) to generate both neutral and profile head pose face images. The head pose information is encoded by facial landmark heatmaps. It not only forms a mask image to guide the generator in learning process but also provides a flexible controllable condition during inference. A couple-agent discriminator is introduced to reinforce on the realism of synthetic arbitrary view faces. Besides the generator and conditional adversarial loss, CAPG-GAN further employs identity preserving loss and total variation regularization to preserve identity information and refine local textures respectively. Quantitative and qualitative experimental results on the Multi-PIE and LFW databases consistently show the superiority of our face rotation method over the state-of-the-art.

Modeling Localness for Self-Attention Networks

Abstract: Self-attention networks have proven to be of profound value for its strength of capturing global dependencies. In this work, we propose to model localness for self-attention networks, which enhances the ability of capturing useful local context. We cast localness modeling as a learnable Gaussian bias, which indicates the central and scope of the local region to be paid more attention. The bias is then incorporated into the original attention distribution to form a revised distribution. To maintain the strength of capturing long distance dependencies while enhance the ability of capturing short-range dependencies, we only apply localness modeling to lower layers of self-attention networks. Quantitative and qualitative analyses on Chinese-English and English-German translation tasks demonstrate the effectiveness and universality of the proposed approach.