Peking University

∙ Beijing , China ∙ 0 followers

Peking University is a major research university in Beijing, China, and a member of the elite C9 League of Chinese universities.

Featured Researchers

Yang Liu
344 publications
Dacheng Tao
293 publications
Lei Zhang
272 publications
Xin Wang
213 publications
Hao Wang
180 publications
Wei Li
162 publications
Qi Tian
150 publications
Xin Li
147 publications
Yu Wang
144 publications
Yi Zhang
140 publications
Dong Wang
139 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
AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks

State-of-the-art methods in the unpaired image-to-image translation are ...
11/27/2019 ∙ by Hao Tang, et al. ∙ 52 ∙ share

read it
Influenza Modeling Based on Massive Feature Engineering and International Flow Deconvolution

In this article, we focus on the analysis of the potential factors drivi...
12/06/2019 ∙ by Ziming Liu, et al. ∙ 47 ∙ share

read it
Randomized ReLU Activation for Uncertainty Estimation of Deep Neural Networks

Deep neural networks (DNNs) have successfully learned useful data repres...
07/15/2021 ∙ by Yufeng Xia, et al. ∙ 47 ∙ share

read it
On the Anomalous Generalization of GANs

Generative models, especially Generative Adversarial Networks (GANs), ha...
09/27/2019 ∙ by Jinchen Xuan, et al. ∙ 46 ∙ share

read it
Relationship-Aware Spatial Perception Fusion for Realistic Scene Layout Generation

The significant progress on Generative Adversarial Networks (GANs) have ...
09/02/2019 ∙ by Hongdong Zheng, et al. ∙ 44 ∙ share

read it
Spatial-Scale Aligned Network for Fine-Grained Recognition

Existing approaches for fine-grained visual recognition focus on learnin...
01/05/2020 ∙ by Lizhao Gao, et al. ∙ 43 ∙ share

read it
When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition with Limited Data

We present a new Deep Dictionary Learning and Coding Network (DDLCN) for...
05/21/2020 ∙ by Hao Tang, et al. ∙ 39 ∙ share

read it
ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Context

Predicting the patient's clinical outcome from the historical electronic...
11/27/2019 ∙ by Liantao Ma, et al. ∙ 35 ∙ share

read it
Unified Generative Adversarial Networks for Controllable Image-to-Image Translation

Controllable image-to-image translation, i.e., transferring an image fro...
12/12/2019 ∙ by Hao Tang, et al. ∙ 32 ∙ 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
Non-local Recurrent Neural Memory for Supervised Sequence Modeling

Typical methods for supervised sequence modeling are built upon the recu...
08/26/2019 ∙ by Canmiao Fu, et al. ∙ 29 ∙ share

read it
Exploring Frequency Domain Interpretation of Convolutional Neural Networks

Many existing interpretation methods of convolutional neural networks (C...
11/27/2019 ∙ by Zhongfan Jia, et al. ∙ 29 ∙ share

read it
Learning Depth-Guided Convolutions for Monocular 3D Object Detection

3D object detection from a single image without LiDAR is a challenging t...
12/10/2019 ∙ by Mingyu Ding, et al. ∙ 28 ∙ share

read it
Asymmetric Generative Adversarial Networks for Image-to-Image Translation

State-of-the-art models for unpaired image-to-image translation with Gen...
12/14/2019 ∙ by Hao Tang, et al. ∙ 28 ∙ share

read it
Differentiable Feature Aggregation Search for Knowledge Distillation

Knowledge distillation has become increasingly important in model compre...
08/02/2020 ∙ by Yushuo Guan, et al. ∙ 28 ∙ share

read it
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry

We propose a self-supervised learning framework for visual odometry (VO)...
08/23/2019 ∙ by Shunkai Li, et al. ∙ 27 ∙ share

read it
Graph-Based Parallel Large Scale Structure from Motion

While Structure from Motion (SfM) achieves great success in 3D reconstru...
12/23/2019 ∙ by Yu Chen, et al. ∙ 27 ∙ share

read it
Generative 3D Part Assembly via Dynamic Graph Learning

Autonomous part assembly is a challenging yet crucial task in 3D compute...
06/14/2020 ∙ by Jialei Huang, et al. ∙ 27 ∙ share

read it
Multi-mapping Image-to-Image Translation via Learning Disentanglement

Recent advances of image-to-image translation focus on learning the one-...
09/17/2019 ∙ by Xiaoming Yu, et al. ∙ 23 ∙ 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
Implicit Normalizing Flows

Normalizing flows define a probability distribution by an explicit inver...
03/17/2021 ∙ by Cheng Lu, et al. ∙ 23 ∙ share

read it
MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation

Cross view feature fusion is the key to address the occlusion problem in...
03/30/2020 ∙ by Rongchang Xie, et al. ∙ 22 ∙ share

read it
Large Margin Multi-modal Multi-task Feature Extraction for Image Classification

The features used in many image analysis-based applications are frequent...
04/08/2019 ∙ by Yong Luo, et al. ∙ 20 ∙ share

read it
Defective Convolutional Layers Learn Robust CNNs

Robustness of convolutional neural networks has recently been highlighte...
11/19/2019 ∙ by Tiange Luo, et al. ∙ 20 ∙ share

read it
GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation

Molecular graph generation is a fundamental problem for drug discovery a...
01/26/2020 ∙ by Chence Shi, et al. ∙ 20 ∙ share

read it
RANDOM MASK: Towards Robust Convolutional Neural Networks

Robustness of neural networks has recently been highlighted by the adver...
07/27/2020 ∙ by Tiange Luo, et al. ∙ 20 ∙ share

read it
Boundary Content Graph Neural Network for Temporal Action Proposal Generation

Temporal action proposal generation plays an important role in video act...
08/04/2020 ∙ by Yueran Bai, et al. ∙ 20 ∙ share

read it
Surgical Skill Assessment on In-Vivo Clinical Data via the Clearness of Operating Field

Surgical skill assessment is important for surgery training and quality ...
08/27/2020 ∙ by Daochang Liu, et al. ∙ 20 ∙ share

read it
Incorporating Human Domain Knowledge in 3D LiDAR-based Semantic Segmentation

This work studies semantic segmentation using 3D LiDAR data. Popular dee...
05/23/2019 ∙ by Jilin Mei, et al. ∙ 19 ∙ share

read it
Single Image Deraining: From Model-Based to Data-Driven and Beyond

Rain removal or deraining methods attempt to restore the clean backgroun...
12/16/2019 ∙ by Wenhan Yang, et al. ∙ 19 ∙ share

read it
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting

We present a lightweight video motion retargeting approach TransMoMo tha...
03/31/2020 ∙ by Zhuoqian Yang, et al. ∙ 19 ∙ share

read it
Image Smoothing via Unsupervised Learning

Image smoothing represents a fundamental component of many disparate com...
11/07/2018 ∙ by Qingnan Fan, et al. ∙ 18 ∙ share

read it
Stroke-based Artistic Rendering Agent with Deep Reinforcement Learning

Excellent painters can use only a few strokes to create a fantastic pain...
03/11/2019 ∙ by Zhewei Huang, et al. ∙ 18 ∙ share

read it
TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding

We aim at solving the problem of predicting people's ideology, or politi...
06/02/2020 ∙ by Zhiping Xiao, et al. ∙ 18 ∙ share

read it
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning

Fusing data from multiple modalities provides more information to train ...
07/14/2020 ∙ by Xinwei Sun, et al. ∙ 18 ∙ share

read it
Reasoning Over Semantic-Level Graph for Fact Checking

We study fact-checking in this paper, which aims to verify a textual cla...
09/09/2019 ∙ by Wanjun Zhong, et al. ∙ 17 ∙ share

read it
Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View

Graph Neural Networks (GNNs) have achieved promising performance on a wi...
09/07/2019 ∙ by Deli Chen, et al. ∙ 17 ∙ share

read it
Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks

Graph Convolutional Neural Networks (GCNNs) extend classical CNNs to gra...
09/11/2019 ∙ by Jiaxiang Tang, et al. ∙ 17 ∙ 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
Mathematical Analysis of Adversarial Attacks

In this paper, we analyze efficacy of the fast gradient sign method (FGS...
11/15/2018 ∙ by Zehao Dou, et al. ∙ 16 ∙ share

read it
Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks

Face anti-spoofing plays a crucial role in protecting face recognition s...
11/28/2018 ∙ by Gusi Te, et al. ∙ 16 ∙ share

read it
L_DMI: An Information-theoretic Noise-robust Loss Function

Accurately annotating large scale dataset is notoriously expensive both ...
09/08/2019 ∙ by Yilun Xu, et al. ∙ 16 ∙ share

read it
Deep Learning for Ultra-Reliable and Low-Latency Communications in 6G Networks

In the future 6th generation networks, ultra-reliable and low-latency co...
02/22/2020 ∙ by Changyang She, et al. ∙ 16 ∙ share

read it
Improve bone age assessment by learning from anatomical local regions

Skeletal bone age assessment (BAA), as an essential imaging examination,...
05/27/2020 ∙ by Dong Wang, et al. ∙ 16 ∙ share

read it
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

In this paper, we propose an end-to-end feature fusion at-tention networ...
11/18/2019 ∙ by Xu Qin, et al. ∙ 15 ∙ share

read it
Recurrent Exposure Generation for Low-Light Face Detection

Face detection from low-light images is challenging due to limited photo...
07/21/2020 ∙ by Jinxiu Liang, et al. ∙ 15 ∙ share

read it
Learning Robust Representation for Clustering through Locality Preserving Variational Discriminative Network

Clustering is one of the fundamental problems in unsupervised learning. ...
12/25/2020 ∙ by Ruixuan Luo, et al. ∙ 15 ∙ share

read it
Learning Disentangled Representation Implicitly via Transformer for Occluded Person Re-Identification

Person re-identification (re-ID) under various occlusions has been a lon...
07/06/2021 ∙ by Mengxi Jia, et al. ∙ 15 ∙ share

read it
Learnable Embedding Space for Efficient Neural Architecture Compression

We propose a method to incrementally learn an embedding space over the d...
02/01/2019 ∙ by Shengcao Cao, et al. ∙ 14 ∙ share

read it