Search Results for author: Ming Liu

Found 189 papers, 71 papers with code

AMLN: Adversarial-based Mutual Learning Network for Online Knowledge Distillation

no code implementations ECCV 2020 Xiaobing Zhang, Shijian Lu, Haigang Gong, Zhipeng Luo, Ming Liu

Online knowledge distillation has attracted increasing interest recently, which jointly learns teacher and student models or an ensemble of student models simultaneously and collaboratively.

Knowledge Distillation Transfer Learning

Less Is More: Domain Adaptation with Lottery Ticket for Reading Comprehension

1 code implementation Findings (EMNLP) 2021 Haichao Zhu, Zekun Wang, Heng Zhang, Ming Liu, Sendong Zhao, Bing Qin

Then, we only fine-tune the lottery subnetwork, a small fraction of the whole parameters, on the annotated target domain data for adaptation.

Domain Adaptation Reading Comprehension

A Survey of Chain of Thought Reasoning: Advances, Frontiers and Future

1 code implementation27 Sep 2023 Zheng Chu, Jingchang Chen, Qianglong Chen, Weijiang Yu, Tao He, Haotian Wang, Weihua Peng, Ming Liu, Bing Qin, Ting Liu

Chain-of-thought reasoning, a cognitive process fundamental to human intelligence, has garnered significant attention in the realm of artificial intelligence and natural language processing.

Beyond Image Borders: Learning Feature Extrapolation for Unbounded Image Composition

1 code implementation ICCV 2023 Xiaoyu Liu, Ming Liu, Junyi Li, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo

In this paper, we circumvent this issue by presenting a joint framework for both unbounded recommendation of camera view and image composition (i. e., UNIC).

Image Cropping

MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces

1 code implementation ICCV 2023 Zhicun Yin, Ming Liu, Xiaoming Li, Hui Yang, Longan Xiao, WangMeng Zuo

To evaluate our proposed MetaF2N, we have collected a real-world low-quality dataset with one or multiple faces in each image, and our MetaF2N achieves superior performance on both synthetic and real-world datasets.

Image Generation Image Super-Resolution +1

Efficient Ray Sampling for Radiance Fields Reconstruction

no code implementations29 Aug 2023 Shilei Sun, Ming Liu, Zhongyi Fan, Yuxue Liu, Chengwei Lv, Liquan Dong, Lingqin Kong

Through this method, not only can the convergence of the network be accelerated, but the spatial geometry of a scene can also be perceived more accurately.

Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders

1 code implementation ICCV 2023 Jie Cheng, Xiaodong Mei, Ming Liu

This study explores the application of self-supervised learning (SSL) to the task of motion forecasting, an area that has not yet been extensively investigated despite the widespread success of SSL in computer vision and natural language processing.

Inductive Bias Motion Forecasting +1

Recent Advances in Hierarchical Multi-label Text Classification: A Survey

no code implementations30 Jul 2023 Rundong Liu, Wenhan Liang, Weijun Luo, Yuxiang Song, He Zhang, Ruohua Xu, Yunfeng Li, Ming Liu

Hierarchical multi-label text classification aims to classify the input text into multiple labels, among which the labels are structured and hierarchical.

Multi Label Text Classification Multi-Label Text Classification +1

Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images

1 code implementation26 Jul 2023 Tianyu Liu, Hao Zhao, Yang Yu, Guyue Zhou, Ming Liu

However, previous studies learned within a sequence of autonomous driving datasets, resulting in unsatisfactory blurring when rotating the car in the simulator.

Autonomous Driving

Adaptive Control of Resource Flow to Optimize Construction Work and Cash Flow via Online Deep Reinforcement Learning

no code implementations20 Jul 2023 Can Jiang, Xin Li, Jia-Rui Lin, Ming Liu, Zhiliang Ma

Therefore, this paper introducess a model and method to adaptive control the resource flows to optimize the work and cash flows of construction projects.


Make Text Unlearnable: Exploiting Effective Patterns to Protect Personal Data

1 code implementation2 Jul 2023 Xinzhe Li, Ming Liu, Shang Gao

This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution.

Question Answering text-classification +1

A Survey on Out-of-Distribution Evaluation of Neural NLP Models

no code implementations27 Jun 2023 Xinzhe Li, Ming Liu, Shang Gao, Wray Buntine

Adversarial robustness, domain generalization and dataset biases are three active lines of research contributing to out-of-distribution (OOD) evaluation on neural NLP models.

Adversarial Robustness Domain Generalization

Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?

1 code implementation27 Jun 2023 Xinzhe Li, Ming Liu, Shang Gao

For Pretrained Language Models (PLMs), their susceptibility to noise has recently been linked to subword segmentation.

SmartTrim: Adaptive Tokens and Parameters Pruning for Efficient Vision-Language Models

no code implementations24 May 2023 Zekun Wang, Jingchang Chen, Wangchunshu Zhou, Ming Liu, Bing Qin

Experimental results demonstrate that SmartTrim significantly reduces the computation overhead (2-3 times) of various VLMs with comparable performance (only a 1-2% degradation) on various vision-language tasks.

Data Augmentation

Automatic Localization and Detection Applicable to Robust Image Watermarking Resisting against Camera Shooting

no code implementations27 Apr 2023 Ming Liu

Furthermore, the proposed scheme is not limited to any specific watermark embedding strategy, allowing for improvements in the watermark embedding and extraction procedure.

Binary stochasticity enabled highly efficient neuromorphic deep learning achieves better-than-software accuracy

no code implementations25 Apr 2023 Yang Li, Wei Wang, Ming Wang, Chunmeng Dou, Zhengyu Ma, Huihui Zhou, Peng Zhang, Nicola Lepri, Xumeng Zhang, Qing Luo, Xiaoxin Xu, Guanhua Yang, Feng Zhang, Ling Li, Daniele Ielmini, Ming Liu

We propose a binary stochastic learning algorithm that modifies all elementary neural network operations, by introducing (i) stochastic binarization of both the forwarding signals and the activation function derivatives, (ii) signed binarization of the backpropagating errors, and (iii) step-wised weight updates.


D2NT: A High-Performing Depth-to-Normal Translator

no code implementations24 Apr 2023 Yi Feng, Bohuan Xue, Ming Liu, Qijun Chen, Rui Fan

Surface normal holds significant importance in visual environmental perception, serving as a source of rich geometric information.

Surface Normal Estimation Vocal Bursts Intensity Prediction

Human Guided Ground-truth Generation for Realistic Image Super-resolution

1 code implementation CVPR 2023 Du Chen, Jie Liang, Xindong Zhang, Ming Liu, Hui Zeng, Lei Zhang

A human guided GT image dataset with both positive and negative samples is then constructed, and a loss function is proposed to train the Real-ISR models.

Image Enhancement Image Super-Resolution

LCE-Calib: Automatic LiDAR-Frame/Event Camera Extrinsic Calibration With A Globally Optimal Solution

1 code implementation17 Mar 2023 Jianhao Jiao, Feiyi Chen, Hexiang Wei, Jin Wu, Ming Liu

This paper proposes an automatic checkerboard-based approach to calibrate extrinsics between a LiDAR and a frame/event camera, where four contributions are presented.

An Efficient Approach to the Online Multi-Agent Path Finding Problem by Using Sustainable Information

no code implementations11 Jan 2023 Mingkai Tang, Boyi Liu, Yuanhang Li, Hongji Liu, Ming Liu, Lujia Wang

The low-level solver, the Sustainable Reverse Safe Interval Path Planning algorithm (SRSIPP), is an efficient single-agent solver that uses previous planning context to reduce duplicate calculations.

Multi-Agent Path Finding

Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography

no code implementations CVPR 2023 Yue Cao, Ming Liu, Shuai Liu, Xiaotao Wang, Lei Lei, WangMeng Zuo

Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling.

Image Denoising

GreenEyes: An Air Quality Evaluating Model based on WaveNet

1 code implementation8 Dec 2022 Kan Huang, Kai Zhang, Ming Liu

Accompanying rapid industrialization, humans are suffering from serious air pollution problems.

Self-Supervised Image Restoration with Blurry and Noisy Pairs

1 code implementation14 Nov 2022 Zhilu Zhang, Rongjian Xu, Ming Liu, Zifei Yan, WangMeng Zuo

By learning in a collaborative manner, the deblurring and denoising tasks in our method can benefit each other.

Deblurring Denoising +1

BigCilin: An Automatic Chinese Open-domain Knowledge Graph with Fine-grained Hypernym-Hyponym Relations

no code implementations7 Nov 2022 Ming Liu, Yaojia LV, Jingrun Zhang, Ruiji Fu, Bing Qin

One is that it supports querying any Chinese named entity and browsing the extracted hypernym-hyponym paths surro-unding the query entity.

How Far are We from Robust Long Abstractive Summarization?

1 code implementation30 Oct 2022 Huan Yee Koh, Jiaxin Ju, He Zhang, Ming Liu, Shirui Pan

For long document abstractive models, we show that the constant strive for state-of-the-art ROUGE results can lead us to generate more relevant summaries but not factual ones.

Abstractive Text Summarization

Kuaipedia: a Large-scale Multi-modal Short-video Encyclopedia

1 code implementation28 Oct 2022 Haojie Pan, Zepeng Zhai, Yuzhou Zhang, Ruiji Fu, Ming Liu, Yangqiu Song, Zhongyuan Wang, Bing Qin

In this paper, we propose Kuaipedia, a large-scale multi-modal encyclopedia consisting of items, aspects, and short videos lined to them, which was extracted from billions of videos of Kuaishou (Kwai), a well-known short-video platform in China.

Entity Linking Entity Typing

A Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration

1 code implementation21 Jul 2022 Ming Liu, Yuxiang Wei, Xiaohe Wu, WangMeng Zuo, Lei Zhang

Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality.

Image Generation Image Restoration

Learning Diverse Tone Styles for Image Retouching

1 code implementation12 Jul 2022 Haolin Wang, Jiawei Zhang, Ming Liu, Xiaohe Wu, WangMeng Zuo

In particular, the style encoder predicts the target style representation of an input image, which serves as the conditional information in the RetouchNet for retouching, while the TSFlow maps the style representation vector into a Gaussian distribution in the forward pass.

Image Retouching

VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion

no code implementations4 Jul 2022 Tao He, Ming Liu, Yixin Cao, Tianwen Jiang, Zihao Zheng, Jingrun Zhang, Sendong Zhao, Bing Qin

In this paper, we solve the sparse KGC from these two motivations simultaneously and handle their respective drawbacks further, and propose a plug-and-play unified framework VEM$^2$L over sparse KGs.

Knowledge Distillation Missing Elements +1

Open-world Semantic Segmentation for LIDAR Point Clouds

1 code implementation4 Jul 2022 Jun Cen, Peng Yun, Shiwei Zhang, Junhao Cai, Di Luan, Michael Yu Wang, Ming Liu, Mingqian Tang

Current methods for LIDAR semantic segmentation are not robust enough for real-world applications, e. g., autonomous driving, since it is closed-set and static.

Autonomous Driving Incremental Learning +2

An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics

1 code implementation3 Jul 2022 Huan Yee Koh, Jiaxin Ju, Ming Liu, Shirui Pan

The empirical analysis includes a study on the intrinsic characteristics of benchmark datasets, a multi-dimensional analysis of summarization models, and a review of the summarization evaluation metrics.

Document Summarization

RNGDet: Road Network Graph Detection by Transformer in Aerial Images

no code implementations16 Feb 2022 Zhenhua Xu, Yuxuan Liu, Lu Gan, Yuxiang Sun, Xinyu Wu, Ming Liu, Lujia Wang

To provide a solution to these problems, we propose a novel approach based on transformer and imitation learning in this paper.

Imitation Learning Motion Planning

Distilled Dual-Encoder Model for Vision-Language Understanding

2 code implementations16 Dec 2021 Zekun Wang, Wenhui Wang, Haichao Zhu, Ming Liu, Bing Qin, Furu Wei

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering.

Question Answering Visual Entailment +2

Temporally Resolution Decrement: Utilizing the Shape Consistency for Higher Computational Efficiency

no code implementations2 Dec 2021 Tianshu Xie, Xuan Cheng, Minghui Liu, Jiali Deng, Xiaomin Wang, Ming Liu

In this paper, we observe that the reduced image retains relatively complete shape semantics but loses extensive texture information.

Open-set 3D Object Detection

no code implementations2 Dec 2021 Jun Cen, Peng Yun, Junhao Cai, Michael Yu Wang, Ming Liu

The first step is solved by the finding that unknown objects are often classified as known objects with low confidence, and we show that the Euclidean distance sum based on metric learning is a better confidence score than the naive softmax probability to differentiate unknown objects from known objects.

3D Object Detection Clustering +2

csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps

no code implementations11 Nov 2021 Zhenhua Xu, Yuxuan Liu, Lu Gan, Xiangcheng Hu, Yuxiang Sun, Ming Liu, Lujia Wang

To provide a solution to the aforementioned problems, in this letter, we propose a novel system termed csBoundary to automatically detect road boundaries at the city scale for HD map annotation.

Autonomous Driving Boundary Detection +1

Leveraging Information Bottleneck for Scientific Document Summarization

no code implementations Findings (EMNLP) 2021 Jiaxin Ju, Ming Liu, Huan Yee Koh, Yuan Jin, Lan Du, Shirui Pan

This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle.

Document Summarization Language Modelling +2

Fine Grained Human Evaluation for English-to-Chinese Machine Translation: A Case Study on Scientific Text

no code implementations13 Sep 2021 Ming Liu, He Zhang, Guanhao Wu

Recent research suggests that neural machine translation (MT) in the news domain has reached human-level performance, but for other professional domains, it is far below the level.

Machine Translation NMT +1

Prototype-Guided Memory Replay for Continual Learning

no code implementations28 Aug 2021 Stella Ho, Ming Liu, Lan Du, Longxiang Gao, Yong Xiang

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge.

Continual Learning Meta-Learning +3

GEDIT: Geographic-Enhanced and Dependency-Guided Tagging for Joint POI and Accessibility Extraction at Baidu Maps

no code implementations20 Aug 2021 Yibo Sun, Jizhou Huang, Chunyuan Yuan, Miao Fan, Haifeng Wang, Ming Liu, Bing Qin

We approach this task as a sequence tagging problem, where the goal is to produce <POI name, accessibility label> pairs from unstructured text.

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision

1 code implementation ICCV 2021 Zhilu Zhang, Haolin Wang, Ming Liu, Ruohao Wang, Jiawei Zhang, WangMeng Zuo

To diminish the effect of color inconsistency in image alignment, we introduce to use a global color mapping (GCM) module to generate an initial sRGB image given the input raw image, which can keep the spatial location of the pixels unchanged, and the target sRGB image is utilized to guide GCM for converting the color towards it.

Optical Flow Estimation

DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks

no code implementations11 Aug 2021 Peide Cai, Hengli Wang, Yuxiang Sun, Ming Liu

Autonomous driving in multi-agent dynamic traffic scenarios is challenging: the behaviors of road users are uncertain and are hard to model explicitly, and the ego-vehicle should apply complicated negotiation skills with them, such as yielding, merging and taking turns, to achieve both safe and efficient driving in various settings.

Autonomous Driving Graph Attention +2

Deep Metric Learning for Open World Semantic Segmentation

1 code implementation ICCV 2021 Jun Cen, Peng Yun, Junhao Cai, Michael Yu Wang, Ming Liu

Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models.

Autonomous Driving Few-Shot Learning +2

SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection

no code implementations30 Jul 2021 Hengli Wang, Rui Fan, Peide Cai, Ming Liu

In particular, SNE-RoadSeg, our previously proposed method based on a surface normal estimator (SNE) and a data-fusion DCNN (RoadSeg), has achieved impressive performance in freespace detection.

Autonomous Driving Surface Normal Estimation +1

Federated Learning Meets Natural Language Processing: A Survey

no code implementations27 Jul 2021 Ming Liu, Stella Ho, Mengqi Wang, Longxiang Gao, Yuan Jin, He Zhang

Recent Natural Language Processing techniques rely on deep learning and large pre-trained language models.

Federated Learning

Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learning

no code implementations18 Jul 2021 Peide Cai, Hengli Wang, Huaiyang Huang, Yuxuan Liu, Ming Liu

In this work, we present a general deep imitative reinforcement learning approach (DIRL), which successfully achieves agile autonomous racing using visual inputs.

Autonomous Driving Car Racing +3

Feature Mining: A Novel Training Strategy for Convolutional Neural Network

no code implementations18 Jul 2021 Tianshu Xie, Xuan Cheng, Xiaomin Wang, Minghui Liu, Jiali Deng, Ming Liu

In this paper, we propose a novel training strategy for convolutional neural network(CNN) named Feature Mining, that aims to strengthen the network's learning of the local feature.

SCV-Stereo: Learning Stereo Matching from a Sparse Cost Volume

no code implementations17 Jul 2021 Hengli Wang, Rui Fan, Ming Liu

Convolutional neural network (CNN)-based stereo matching approaches generally require a dense cost volume (DCV) for disparity estimation.

Disparity Estimation Stereo Matching

Go Small and Similar: A Simple Output Decay Brings Better Performance

no code implementations12 Jun 2021 Xuan Cheng, Tianshu Xie, Xiaomin Wang, Jiali Deng, Minghui Liu, Ming Liu

Regularization and data augmentation methods have been widely used and become increasingly indispensable in deep learning training.

Data Augmentation

Self-supervised Feature Enhancement: Applying Internal Pretext Task to Supervised Learning

no code implementations9 Jun 2021 Yuhang Yang, Zilin Ding, Xuan Cheng, Xiaomin Wang, Ming Liu

In this paper, we show that feature transformations within CNNs can also be regarded as supervisory signals to construct the self-supervised task, called \emph{internal pretext task}.

Self-Supervised Learning

White Paper Assistance: A Step Forward Beyond the Shortcut Learning

no code implementations8 Jun 2021 Xuan Cheng, Tianshu Xie, Xiaomin Wang, Jiali Deng, Minghui Liu, Ming Liu

The promising performances of CNNs often overshadow the need to examine whether they are doing in the way we are actually interested.

imbalanced classification

DADgraph: A Discourse-aware Dialogue Graph Neural Network for Multiparty Dialogue Machine Reading Comprehension

no code implementations26 Apr 2021 Jiaqi Li, Ming Liu, Zihao Zheng, Heng Zhang, Bing Qin, Min-Yen Kan, Ting Liu

Multiparty Dialogue Machine Reading Comprehension (MRC) differs from traditional MRC as models must handle the complex dialogue discourse structure, previously unconsidered in traditional MRC.

Machine Reading Comprehension Question Answering

Comparing Representations in Tracking for Event Camera-based SLAM

1 code implementation20 Apr 2021 Jianhao Jiao, Huaiyang Huang, Liang Li, Zhijian He, Yilong Zhu, Ming Liu

This paper investigates two typical image-type representations for event camera-based tracking: time surface (TS) and event map (EM).

End-to-End Interactive Prediction and Planning with Optical Flow Distillation for Autonomous Driving

no code implementations18 Apr 2021 Hengli Wang, Peide Cai, Rui Fan, Yuxiang Sun, Ming Liu

With the recent advancement of deep learning technology, data-driven approaches for autonomous car prediction and planning have achieved extraordinary performance.

Autonomous Driving Optical Flow Estimation +1

Learning Interpretable End-to-End Vision-Based Motion Planning for Autonomous Driving with Optical Flow Distillation

no code implementations18 Apr 2021 Hengli Wang, Peide Cai, Yuxiang Sun, Lujia Wang, Ming Liu

To address this problem, we propose an interpretable end-to-end vision-based motion planning approach for autonomous driving, referred to as IVMP.

Autonomous Driving Motion Planning +1

3D Surfel Map-Aided Visual Relocalization with Learned Descriptors

no code implementations8 Apr 2021 Haoyang Ye, Huaiyang Huang, Marco Hutter, Timothy Sandy, Ming Liu

In this paper, we introduce a method for visual relocalization using the geometric information from a 3D surfel map.

Camera Relocalization

Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving

1 code implementation31 Mar 2021 Zhenhua Xu, Yuxiang Sun, Ming Liu

So in this paper, we propose a new benchmark dataset, named \textit{Topo-boundary}, for offline topological road-boundary detection.

Autonomous Driving Boundary Detection +1

iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving

1 code implementation31 Mar 2021 Zhenhua Xu, Yuxiang Sun, Ming Liu

We find that the visual appearances between road areas and off-road areas are usually different in aerial images, so we propose a novel solution to detect road curbs off-line using aerial images.

Autonomous Driving Imitation Learning +1

Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions

no code implementations29 Mar 2021 Xuan Cheng, Tianshu Xie, Xiaomin Wang, Qifeng Weng, Minghui Liu, Jiali Deng, Ming Liu

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs).

Image Classification

FocusedDropout for Convolutional Neural Network

no code implementations29 Mar 2021 Tianshu Xie, Minghui Liu, Jiali Deng, Xuan Cheng, Xiaomin Wang, Ming Liu

In convolutional neural network (CNN), dropout cannot work well because dropped information is not entirely obscured in convolutional layers where features are correlated spatially.

YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

1 code implementation17 Mar 2021 Yuxuan Liu, Lujia Wang, Ming Liu

Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs.

3D Object Detection From Stereo Images Disparity Estimation +2

PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching

no code implementations12 Mar 2021 Hengli Wang, Rui Fan, Peide Cai, Ming Liu

Supervised learning with deep convolutional neural networks (DCNNs) has seen huge adoption in stereo matching.

Stereo Matching

Cut-Thumbnail: A Novel Data Augmentation for Convolutional Neural Network

1 code implementation9 Mar 2021 Tianshu Xie, Xuan Cheng, Minghui Liu, Jiali Deng, Xiaomin Wang, Ming Liu

In this paper, we propose a novel data augmentation strategy named Cut-Thumbnail, that aims to improve the shape bias of the network.

Classification Data Augmentation +4

Dynamic Fusion Module Evolves Drivable Area and Road Anomaly Detection: A Benchmark and Algorithms

1 code implementation3 Mar 2021 Hengli Wang, Rui Fan, Yuxiang Sun, Ming Liu

Therefore, in this paper, we first build a drivable area and road anomaly detection benchmark for ground mobile robots, evaluating the existing state-of-the-art single-modal and data-fusion semantic segmentation CNNs using six modalities of visual features.

Anomaly Detection Self-Driving Cars +1

AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention

no code implementations14 Jan 2021 Congcong Liu, Yuying Chen, Ming Liu, Bertram E. Shi

We suggest that introducing an attention mechanism to infer the importance of different neighbors is critical for accurate trajectory prediction in scenes with varying crowd size.

Pedestrian Trajectory Prediction Trajectory Prediction

Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation

no code implementations14 Dec 2020 Rui Fan, Hengli Wang, Peide Cai, Jin Wu, Mohammud Junaid Bocus, Lei Qiao, Ming Liu

Therefore, this paper mainly explores an effective training data augmentation approach that can be employed to improve the overall DCNN performance, when additional images captured from different views are available.

Data Augmentation Semantic Segmentation

Two-Stage Single Image Reflection Removal with Reflection-Aware Guidance

1 code implementation2 Dec 2020 Yu Li, Ming Liu, Yaling Yi, Qince Li, Dongwei Ren, WangMeng Zuo

To be specific, the reflection layer is firstly estimated due to that it generally is much simpler and is relatively easier to estimate.

Reflection Removal Vocal Bursts Valence Prediction

DiGNet: Learning Scalable Self-Driving Policies for Generic Traffic Scenarios with Graph Neural Networks

no code implementations13 Nov 2020 Peide Cai, Hengli Wang, Yuxiang Sun, Ming Liu

Traditional decision and planning frameworks for self-driving vehicles (SDVs) scale poorly in new scenarios, thus they require tedious hand-tuning of rules and parameters to maintain acceptable performance in all foreseeable cases.


Geometric Structure Aided Visual Inertial Localization

1 code implementation9 Nov 2020 Huaiyang Huang, Haoyang Ye, Jianhao Jiao, Yuxiang Sun, Ming Liu

To take the advantages of both, in this work, we present a complete visual inertial localization system based on a hybrid map representation to reduce the computational cost and increase the positioning accuracy.

Autonomous Navigation Visual Localization

Robust Odometry and Mapping for Multi-LiDAR Systems with Online Extrinsic Calibration

2 code implementations27 Oct 2020 Jianhao Jiao, Haoyang Ye, Yilong Zhu, Ming Liu

This paper proposes a system to achieve robust and simultaneous extrinsic calibration, odometry, and mapping for multiple LiDARs.

Simultaneous Localization and Mapping

SciSummPip: An Unsupervised Scientific Paper Summarization Pipeline

no code implementations19 Oct 2020 Jiaxin Ju, Ming Liu, Longxiang Gao, Shirui Pan

The Scholarly Document Processing (SDP) workshop is to encourage more efforts on natural language understanding of scientific task.

Clustering Graph Clustering +5

Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs

1 code implementation EMNLP 2020 Jueqing Lu, Lan Du, Ming Liu, Joanna Dipnall

Few/Zero-shot learning is a big challenge of many classifications tasks, where a classifier is required to recognise instances of classes that have very few or even no training samples.

Document Classification General Classification +3

Wound and episode level readmission risk or weeks to readmit: Why do patients get readmitted? How long does it take for a patient to get readmitted?

no code implementations5 Oct 2020 Subba Reddy Oota, Nafisur Rahman, Shahid Saleem Mohammed, Jeffrey Galitz, Ming Liu

On a combined wound & episode-level data set of patient's wound care information, our extended autoprognosis achieves a recall of 92 and a precision of 92 for the predicting a patient's re-admission risk.


Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation

no code implementations2 Oct 2020 M Usman Maqbool Bhutta, Shoaib Aslam, Peng Yun, Jianhao Jiao, Ming Liu

We present a robust semi-supervised learning framework for intelligent micro-scaled localization and classification of defects on a 16K pixel image of smartphone glass.

General Classification

Loop-box: Multi-Agent Direct SLAM Triggered by Single Loop Closure for Large-Scale Mapping

no code implementations29 Sep 2020 M Usman Maqbool Bhutta, Manohar Kuse, Rui Fan, Yanan Liu, Ming Liu

We develop a generic method for the keychallenging scenarios in multi-agent 3D mapping based on different camera systems.

3D Reconstruction

MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving

2 code implementations29 Sep 2020 Jianhao Jiao, Peng Yun, Lei Tai, Ming Liu

To minimize the detrimental effect of extrinsic perturbation, we propagate an uncertainty prior on each point of input point clouds, and use this information to boost an approach for 3D geometric tasks.

3D Object Detection Autonomous Driving +1

Activate or Not: Learning Customized Activation

4 code implementations CVPR 2021 Ningning Ma, Xiangyu Zhang, Ming Liu, Jian Sun

We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not.

object-detection Object Detection +1

Unpaired Learning of Deep Image Denoising

2 code implementations ECCV 2020 Xiaohe Wu, Ming Liu, Yue Cao, Dongwei Ren, WangMeng Zuo

As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set.

Image Denoising Knowledge Distillation +1

ATG-PVD: Ticketing Parking Violations on A Drone

no code implementations21 Aug 2020 Hengli Wang, Yuxuan Liu, Huaiyang Huang, Yuheng Pan, Wenbin Yu, Jialin Jiang, Dianbin Lyu, Mohammud J. Bocus, Ming Liu, Ioannis Pitas, Rui Fan

In this paper, we introduce a novel suspect-and-investigate framework, which can be easily embedded in a drone for automated parking violation detection (PVD).

Optical Flow Estimation

We Learn Better Road Pothole Detection: from Attention Aggregation to Adversarial Domain Adaptation

1 code implementation16 Aug 2020 Rui Fan, Hengli Wang, Mohammud J. Bocus, Ming Liu

The experimental results demonstrate that, firstly, the transformed disparity (or inverse depth) images become more informative; secondly, AA-UNet and AA-RTFNet, our best performing implementations, respectively outperform all other state-of-the-art single-modal and data-fusion networks for road pothole detection; and finally, the training set augmentation technique based on adversarial domain adaptation not only improves the accuracy of the state-of-the-art semantic segmentation networks, but also accelerates their convergence.

Domain Adaptation Semantic Segmentation +1

Learning Flow-based Feature Warping for Face Frontalization with Illumination Inconsistent Supervision

1 code implementation ECCV 2020 Yuxiang Wei, Ming Liu, Haolin Wang, Ruifeng Zhu, Guosheng Hu, WangMeng Zuo

Despite recent advances in deep learning-based face frontalization methods, photo-realistic and illumination preserving frontal face synthesis is still challenging due to large pose and illumination discrepancy during training.

Face Generation

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

1 code implementation17 Jul 2020 Jinming Zhao, Ming Liu, Longxiang Gao, Yuan Jin, Lan Du, He Zhao, He Zhang, Gholamreza Haffari

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains.

Clustering Document Summarization +1

GMMLoc: Structure Consistent Visual Localization with Gaussian Mixture Models

1 code implementation24 Jun 2020 Huaiyang Huang, Haoyang Ye, Yuxiang Sun, Ming Liu

Incorporating prior structure information into the visual state estimation could generally improve the localization performance.

Simultaneous Localization and Mapping Visual Localization

6 nm super-resolution optical transmission and scattering spectroscopic imaging of carbon nanotubes using a nanometer-scale white light source

no code implementations8 Jun 2020 Xuezhi Ma, Qiushi Liu, Ning Yu, Da Xu, Sanggon Kim, Zebin Liu, Kaili Jiang, Bryan M. Wong, Ruoxue Yan, Ming Liu

Optical hyperspectral imaging based on absorption and scattering of photons at the visible and adjacent frequencies denotes one of the most informative and inclusive characterization methods in material research.

Super-Resolution Optics Materials Science

Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator

2 code implementations17 May 2020 Rui Fan, Hengli Wang, Bohuan Xue, Huaiyang Huang, YuAn Wang, Ming Liu, Ioannis Pitas

To evaluate the performance of our proposed SNE, we created three large-scale synthetic datasets (easy, medium and hard) using 24 3D mesh models, each of which is used to generate 1800--2500 pairs of depth images (resolution: 480X640 pixels) and the corresponding ground-truth surface normal maps from different views.

Probabilistic End-to-End Vehicle Navigation in Complex Dynamic Environments with Multimodal Sensor Fusion

no code implementations5 May 2020 Peide Cai, Sukai Wang, Yuxiang Sun, Ming Liu

All-day and all-weather navigation is a critical capability for autonomous driving, which requires proper reaction to varied environmental conditions and complex agent behaviors.

Autonomous Driving Imitation Learning +1

VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments

1 code implementation27 Apr 2020 Peide Cai, Yuxiang Sun, Hengli Wang, Ming Liu

Traditional methods for autonomous driving are implemented with many building blocks from perception, planning and control, making them difficult to generalize to varied scenarios due to complex assumptions and interdependencies.

Autonomous Driving Imitation Learning +1

Deep Adaptive Inference Networks for Single Image Super-Resolution

1 code implementation8 Apr 2020 Ming Liu, Zhilu Zhang, Liya Hou, WangMeng Zuo, Lei Zhang

Nonetheless, content and resource adaptive model is more preferred, and it is encouraging to apply simpler and efficient networks to the easier regions with less details and the scenarios with restricted efficiency constraints.

Image Super-Resolution

COVID-19 Docking Server: A meta server for docking small molecules, peptides and antibodies against potential targets of COVID-19

no code implementations29 Feb 2020 Ren Kong, Guangbo Yang, Rui Xue, Ming Liu, Feng Wang, Jianping Hu, Xiaoqiang Guo, Shan Chang

Motivation: The coronavirus disease 2019 (COVID-19) caused by a new type of coronavirus has been emerging from China and led to thousands of death globally since December 2019.

Drug Discovery

Monocular Direct Sparse Localization in a Prior 3D Surfel Map

no code implementations23 Feb 2020 Haoyang Ye, Huaiyang Huang, Ming Liu

The tracked points with and without the global planar information involve both global and local constraints of frames to the system.

Camera Localization

Robust Lane Marking Detection Algorithm Using Drivable Area Segmentation and Extended SLT

no code implementations20 Nov 2019 Umar Ozgunalp, Rui Fan, Shanshan Cheng, Yuxiang Sun, Weixun Zuo, Yilong Zhu, Bohuan Xue, Linwei Zheng, Qing Liang, Ming Liu

In this paper, a robust lane detection algorithm is proposed, where the vertical road profile of the road is estimated using dynamic programming from the v-disparity map and, based on the estimated profile, the road area is segmented.

Lane Detection

An Annotation Scheme of A Large-scale Multi-party Dialogues Dataset for Discourse Parsing and Machine Comprehension

no code implementations8 Nov 2019 Jiaqi Li, Ming Liu, Bing Qin, Zihao Zheng, Ting Liu

In this paper, we propose the scheme for annotating large-scale multi-party chat dialogues for discourse parsing and machine comprehension.

Discourse Parsing Machine Reading Comprehension

Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification

no code implementations IJCNLP 2019 Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Tong Xu, Ming Liu

Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context.

Classification General Classification +2

Federated Transfer Reinforcement Learning for Autonomous Driving

no code implementations14 Oct 2019 Xinle Liang, Yang Liu, Tianjian Chen, Ming Liu, Qiang Yang

Reinforcement learning (RL) is widely used in autonomous driving tasks and training RL models typically involves in a multi-step process: pre-training RL models on simulators, uploading the pre-trained model to real-life robots, and fine-tuning the weight parameters on robot vehicles.

Autonomous Driving reinforcement-learning +2

Variational Auto-encoder Based Bayesian Poisson Tensor Factorization for Sparse and Imbalanced Count Data

no code implementations12 Oct 2019 Yuan Jin, Ming Liu, Yunfeng Li, Ruohua Xu, Lan Du, Longxiang Gao, Yong Xiang

Under synthetic data evaluation, VAE-BPTF tended to recover the right number of latent factors and posterior parameter values.

Road Damage Detection Based on Unsupervised Disparity Map Segmentation

1 code implementation11 Oct 2019 Rui Fan, Ming Liu

This paper presents a novel road damage detection algorithm based on unsupervised disparity map segmentation.

Road Damage Detection

Utilizing Eye Gaze to Enhance the Generalization of Imitation Networks to Unseen Environments

no code implementations10 Jul 2019 Congcong Liu, Yuying Chen, Lei Tai, Ming Liu, Bertram Shi

Vision-based autonomous driving through imitation learning mimics the behaviors of human drivers by training on pairs of data of raw driver-view images and actions.

Autonomous Driving Imitation Learning

Learning How to Active Learn by Dreaming

1 code implementation ACL 2019 Thuy-Trang Vu, Ming Liu, Dinh Phung, Gholamreza Haffari

Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.

Active Learning named-entity-recognition +5

Movable-Object-Aware Visual SLAM via Weakly Supervised Semantic Segmentation

no code implementations9 Jun 2019 Ting Sun, Yuxiang Sun, Ming Liu, Dit-yan Yeung

Moving objects can greatly jeopardize the performance of a visual simultaneous localization and mapping (vSLAM) system which relies on the static-world assumption.

Simultaneous Localization and Mapping Weakly supervised Semantic Segmentation +1

Key Ingredients of Self-Driving Cars

no code implementations7 Jun 2019 Rui Fan, Jianhao Jiao, Haoyang Ye, Yang Yu, Ioannis Pitas, Ming Liu

Over the past decade, many research articles have been published in the area of autonomous driving.

Autonomous Driving Self-Driving Cars

A Robust Roll Angle Estimation Algorithm Based on Gradient Descent

no code implementations5 Jun 2019 Rui Fan, Lujia Wang, Ming Liu, Ioannis Pitas

This paper presents a robust roll angle estimation algorithm, which is developed from our previously published work, where the roll angle was estimated from a dense disparity map by minimizing a global energy using golden section search algorithm.

Automatic Calibration of Multiple 3D LiDARs in Urban Environments

no code implementations13 May 2019 Jianhao Jiao, Yang Yu, Qinghai Liao, Haoyang Ye, Ming Liu

Multiple LiDARs have progressively emerged on autonomous vehicles for rendering a wide field of view and dense measurements.

Autonomous Vehicles Translation

A Novel Dual-Lidar Calibration Algorithm Using Planar Surfaces

no code implementations27 Apr 2019 Jianhao Jiao, Qinghai Liao, Yilong Zhu, Tianyu Liu, Yang Yu, Rui Fan, Lujia Wang, Ming Liu

Multiple lidars are prevalently used on mobile vehicles for rendering a broad view to enhance the performance of localization and perception systems.


STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing

5 code implementations CVPR 2019 Ming Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, WangMeng Zuo, Shilei Wen

Arbitrary attribute editing generally can be tackled by incorporating encoder-decoder and generative adversarial networks.


Gaze Training by Modulated Dropout Improves Imitation Learning

no code implementations17 Apr 2019 Yuying Chen, Congcong Liu, Lei Tai, Ming Liu, Bertram E. Shi

The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior.

Autonomous Driving Imitation Learning

Tightly Coupled 3D Lidar Inertial Odometry and Mapping

1 code implementation15 Apr 2019 Haoyang Ye, Yuying Chen, Ming Liu

By sensor fusion, we can compensate the deficiencies of stand-alone sensors and provide more reliable estimations.

Motion Estimation Sensor Fusion

RTFNet: RGB-Thermal Fusion Network for Semantic Segmentation of Urban Scenes

no code implementations IEEE ROBOTICS AND AUTOMATION LETTERS 2019 Yuxiang Sun, Weixun Zuo, Ming Liu

In order to enable robust and accurate semantic segmentation for autonomous vehicles, we take the advantage of thermal images and fuse both the RGB and thermal information in a novel deep neural network.

Autonomous Vehicles Semantic Segmentation +1

Attribute Acquisition in Ontology based on Representation Learning of Hierarchical Classes and Attributes

no code implementations8 Mar 2019 Tianwen Jiang, Ming Liu, Bing Qin, Ting Liu

This paper investigates an attention-based automatic paradigm called TransATT for attribute acquisition, by learning the representation of hierarchical classes and attributes in Chinese ontology.

Representation Learning

Using DP Towards A Shortest Path Problem-Related Application

no code implementations7 Mar 2019 Jianhao Jiao, Rui Fan, Han Ma, Ming Liu

We apply the designed model and proposed an algorithm for detecting lanes by formulating it as the shortest path problem.

Autonomous Driving Lane Detection

PointIT: A Fast Tracking Framework Based on 3D Instance Segmentation

no code implementations18 Feb 2019 Yu-An Wang, Yang Yu, Ming Liu

Finally, we extend the Sort algorithm with this instance framework to realize tracking in the 3D LiDAR point cloud data.

3D Instance Segmentation Semantic Segmentation

Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems

no code implementations19 Jan 2019 Boyi Liu, Lujia Wang, Ming Liu

To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRL).

reinforcement-learning Reinforcement Learning (RL) +2

Learning Symmetry Consistent Deep CNNs for Face Completion

1 code implementation19 Dec 2018 Xiaoming Li, Ming Liu, Jieru Zhu, WangMeng Zuo, Meng Wang, Guosheng Hu, Lei Zhang

As for missing pixels on both of half-faces, we present a generative reconstruction subnet together with a perceptual symmetry loss to enforce symmetry consistency of recovered structures.

Face Recognition Facial Inpainting

Semi-Semantic Line-Cluster Assisted Monocular SLAM for Indoor Environments

no code implementations5 Nov 2018 Ting Sun, Dezhen Song, Dit-yan Yeung, Ming Liu

In the back end, we optimize the map imposing the constraint that the line segments of the same cluster should be the same.

Simultaneous Localization and Mapping

Point-cloud-based place recognition using CNN feature extraction

no code implementations23 Oct 2018 Ting Sun, Ming Liu, Haoyang Ye, Dit-yan Yeung

This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction.

Neural Speech Synthesis with Transformer Network

5 code implementations19 Sep 2018 Naihan Li, Shujie Liu, Yanqing Liu, Sheng Zhao, Ming Liu, Ming Zhou

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-the-art performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using current recurrent neural networks (RNNs).

Ranked #9 on Text-To-Speech Synthesis on LJSpeech (using extra training data)

Machine Translation NMT +2