HUAWEI Technologies Co., Ltd.

∙ Shenzhen , China ∙ 0 followers

The Huawei Consumer BG is dedicated to delivering the latest technologies to consumers around the world. Huawei unveiled HUAWEI Mate 30 series and Kirin 990 series in 2019, which opens a new era of 5G. Read more about Huawei Consumer Business Group's milestones and achievements over the years in our About Us page

Featured Researchers

Jun Wang
138 publications
Qi Tian
93 publications
Hao Chen
92 publications
Jian Zhang
86 publications
Mérouane Debbah
62 publications
Bin Liu
57 publications
Chang Xu
57 publications
Bin Li
54 publications
Min Zhang
47 publications
Zhaopeng Tu
42 publications
Lei Chen
42 publications

Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks

Deep neural networks often consist of a great number of trainable parame...
02/23/2020 ∙ by Yehui Tang, et al. ∙ 72 ∙ share

read it
Appending Adversarial Frames for Universal Video Attack

There have been many efforts in attacking image classification models wi...
12/10/2019 ∙ by Zhikai Chen, et al. ∙ 34 ∙ share

read it
AdderNet: Do We Really Need Multiplications in Deep Learning?

Compared with cheap addition operation, multiplication operation is of m...
12/31/2019 ∙ by Hanting Chen, et al. ∙ 31 ∙ share

read it
Revisit Knowledge Distillation: a Teacher-free Framework

Knowledge Distillation (KD) aims to distill the knowledge of a cumbersom...
09/25/2019 ∙ by Li Yuan, et al. ∙ 29 ∙ share

read it
Few-shot Adaptive Faster R-CNN

To mitigate the detection performance drop caused by domain shift, we ai...
03/22/2019 ∙ by Tao Wang, et al. ∙ 24 ∙ share

read it
Is Fast Adaptation All You Need?

Gradient-based meta-learning has proven to be highly effective at learni...
10/03/2019 ∙ by Khurram Javed, et al. ∙ 24 ∙ share

read it
RefinedMPL: Refined Monocular PseudoLiDAR for 3D Object Detection in Autonomous Driving

In this paper, we strive for solving the ambiguities arisen by the astou...
11/21/2019 ∙ by Jean Marie Uwabeza Vianney, et al. ∙ 24 ∙ share

read it
GhostNet: More Features from Cheap Operations

Deploying convolutional neural networks (CNNs) on embedded devices is di...
11/27/2019 ∙ by Kai Han, et al. ∙ 23 ∙ share

read it
AdvHat: Real-world adversarial attack on ArcFace Face ID system

In this paper we propose a novel easily reproducible technique to attack...
08/23/2019 ∙ by Stepan Komkov, et al. ∙ 21 ∙ share

read it
Less Is Better: Unweighted Data Subsampling via Influence Function

In the time of Big Data, training complex models on large-scale data set...
12/03/2019 ∙ by Zifeng Wang, et al. ∙ 20 ∙ share

read it
Generate High-Resolution Adversarial Samples by Identifying Effective Features

As the prevalence of deep learning in computer vision, adversarial sampl...
01/21/2020 ∙ by Sizhe Chen, et al. ∙ 19 ∙ share

read it
CARS: Continuous Evolution for Efficient Neural Architecture Search

Searching techniques in most of existing neural architecture search (NAS...
09/11/2019 ∙ by Zhaohui Yang, et al. ∙ 17 ∙ share

read it
Real-world attack on MTCNN face detection system

Recent studies proved that deep learning approaches achieve remarkable r...
10/14/2019 ∙ by Edgar Kaziakhmedov, et al. ∙ 16 ∙ share

read it
Scalable NAS with Factorizable Architectural Parameters

Neural architecture search (NAS) is an emerging topic in machine learnin...
12/31/2019 ∙ by Lanfei Wang, et al. ∙ 16 ∙ share

read it
Pose Agnostic Cross-spectral Hallucination via Disentangling Independent Factors

The cross-sensor gap is one of the challenges that arise much research i...
09/10/2019 ∙ by Boyan Duan, et al. ∙ 15 ∙ share

read it
AI Benchmark: Running Deep Neural Networks on Android Smartphones

Over the last years, the computational power of mobile devices such as s...
10/02/2018 ∙ by Andrey Ignatov, et al. ∙ 14 ∙ share

read it
SteReFo: Efficient Image Refocusing with Stereo Vision

Whether to attract viewer attention to a particular object, give the imp...
09/29/2019 ∙ by Benjamin Busam, et al. ∙ 14 ∙ share

read it
Learning beyond Predefined Label Space via Bayesian Nonparametric Topic Modelling

In real world machine learning applications, testing data may contain so...
10/10/2019 ∙ by Changying Du, et al. ∙ 14 ∙ share

read it
Distilling portable Generative Adversarial Networks for Image Translation

Despite Generative Adversarial Networks (GANs) have been widely used in ...
03/07/2020 ∙ by Hanting Chen, et al. ∙ 13 ∙ share

read it
PPD: Permutation Phase Defense Against Adversarial Examples in Deep Learning

Deep neural networks have demonstrated cutting edge performance on vario...
12/25/2018 ∙ by Mehdi Jafarnia-Jahromi, et al. ∙ 12 ∙ share

read it
Discernible Compressed Images via Deep Perception Consistency

Image compression, as one of the fundamental low-level image processing ...
02/17/2020 ∙ by Zhaohui Yang, et al. ∙ 12 ∙ share

read it
Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning

Social psychology and real experiences show that cognitive consistency p...
12/03/2019 ∙ by Hangyu Mao, et al. ∙ 11 ∙ share

read it
Adversarial AutoAugment

Data augmentation (DA) has been widely utilized to improve generalizatio...
12/24/2019 ∙ by Xinyu Zhang, et al. ∙ 11 ∙ share

read it
Image Generation from Freehand Scene Sketches

We introduce the first method for automatic image generation from scene-...
03/05/2020 ∙ by Chengying Gao, et al. ∙ 11 ∙ share

read it
Data-Free Learning of Student Networks

Learning portable neural networks is very essential for computer vision ...
04/02/2019 ∙ by Hanting Chen, et al. ∙ 10 ∙ share

read it
RNAS: Architecture Ranking for Powerful Networks

Neural Architecture Search (NAS) is attractive for automatically produci...
09/30/2019 ∙ by Yixing Xu, et al. ∙ 10 ∙ share

read it
Super Resolution Using Segmentation-Prior Self-Attention Generative Adversarial Network

Convolutional Neural Network (CNN) is intensively implemented to solve s...
03/07/2020 ∙ by Yuxin Zhang, et al. ∙ 10 ∙ share

read it
Multimodal Unified Attention Networks for Vision-and-Language Interactions

Learning an effective attention mechanism for multimodal data is importa...
08/12/2019 ∙ by Zhou Yu, et al. ∙ 9 ∙ share

read it
Perception as prediction using general value functions in autonomous driving applications

We propose and demonstrate a framework called perception as prediction f...
01/24/2020 ∙ by Daniel Graves, et al. ∙ 9 ∙ share

read it
Adversarial Domain Adaptation with Domain Mixup

Recent works on domain adaptation reveal the effectiveness of adversaria...
12/04/2019 ∙ by Minghao Xu, et al. ∙ 8 ∙ share

read it
Positive-Unlabeled Compression on the Cloud

Many attempts have been done to extend the great success of convolutiona...
09/21/2019 ∙ by Yixing Xu, et al. ∙ 7 ∙ share

read it
Phase Collaborative Network for Multi-Phase Medical Imaging Segmentation

Integrating multi-phase information is an effective way of boosting visu...
11/28/2018 ∙ by Huangjie Zheng, et al. ∙ 6 ∙ share

read it
Aligning Linguistic Words and Visual Semantic Units for Image Captioning

Image captioning attempts to generate a sentence composed of several lin...
08/06/2019 ∙ by Longteng Guo, et al. ∙ 6 ∙ share

read it
Generative Question Refinement with Deep Reinforcement Learning in Retrieval-based QA System

In real-world question-answering (QA) systems, ill-formed questions, suc...
08/13/2019 ∙ by Ye Liu, et al. ∙ 6 ∙ share

read it
On Positive-Unlabeled Classification in GAN

This paper defines a positive and unlabeled classification problem for s...
02/04/2020 ∙ by Tianyu Guo, et al. ∙ 6 ∙ share

read it
Circumventing Outliers of AutoAugment with Knowledge Distillation

AutoAugment has been a powerful algorithm that improves the accuracy of ...
03/25/2020 ∙ by Longhui Wei, et al. ∙ 6 ∙ share

read it
Learning Instance-wise Sparsity for Accelerating Deep Models

Exploring deep convolutional neural networks of high efficiency and low ...
07/27/2019 ∙ by Chuanjian Liu, et al. ∙ 5 ∙ share

read it
Two-Stream Video Classification with Cross-Modality Attention

Fusing multi-modality information is known to be able to effectively bri...
08/01/2019 ∙ by Lu Chi, et al. ∙ 5 ∙ share

read it
Dialog State Tracking with Reinforced Data Augmentation

Neural dialog state trackers are generally limited due to the lack of qu...
08/21/2019 ∙ by Yichun Yin, et al. ∙ 5 ∙ share

read it
Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation

Inspired by the success of adversarial learning, we propose a new end-to...
08/15/2019 ∙ by Mihai Marian Puscas, et al. ∙ 4 ∙ share

read it
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection

Neural Architecture Search (NAS) has achieved great success in image cla...
03/26/2020 ∙ by Jianyuan Guo, et al. ∙ 4 ∙ share

read it
Distilling Object Detectors with Fine-grained Feature Imitation

State-of-the-art CNN based recognition models are often computationally ...
06/09/2019 ∙ by Tao Wang, et al. ∙ 3 ∙ share

read it
VRLS: A Unified Reinforcement Learning Scheduler for Vehicle-to-Vehicle Communications

Vehicle-to-vehicle (V2V) communications have distinct challenges that ne...
07/22/2019 ∙ by Taylan Şahin, et al. ∙ 3 ∙ share

read it
Attribute Aware Pooling for Pedestrian Attribute Recognition

This paper expands the strength of deep convolutional neural networks (C...
07/27/2019 ∙ by Kai Han, et al. ∙ 3 ∙ share

read it
α Belief Propagation as Fully Factorized Approximation

Belief propagation (BP) can do exact inference in loop-free graphs, but ...
08/23/2019 ∙ by Dong Liu, et al. ∙ 3 ∙ share

read it
NODE: Extreme Low Light Raw Image Denoising using a Noise Decomposition Network

Denoising extreme low light images is a challenging task due to the high...
09/11/2019 ∙ by Hao Guan, et al. ∙ 3 ∙ share

read it
Real-Time Lane ID Estimation Using Recurrent Neural Networks With Dual Convention

Acquiring information about the road lane structure is a crucial step fo...
01/14/2020 ∙ by Ibrahim Halfaoui, et al. ∙ 3 ∙ share

read it
Latency-Aware Differentiable Neural Architecture Search

Differentiable neural architecture search methods became popular in auto...
01/17/2020 ∙ by Yuhui Xu, et al. ∙ 3 ∙ share

read it
Defending Adversarial Attacks by Correcting logits

Generating and eliminating adversarial examples has been an intriguing t...
06/26/2019 ∙ by Yifeng Li, et al. ∙ 2 ∙ share

read it
Deep Modular Co-Attention Networks for Visual Question Answering

Visual Question Answering (VQA) requires a fine-grained and simultaneous...
06/25/2019 ∙ by Zhou Yu, et al. ∙ 2 ∙ share

read it