Search Results for author: Zhen Li

Found 149 papers, 70 papers with code

Reciprocal Learning of Knowledge Retriever and Response Ranker for Knowledge-Grounded Conversations

no code implementations COLING 2022 Jiazhan Feng, Chongyang Tao, Zhen Li, Chang Liu, Tao Shen, Dongyan Zhao

In this paper, we propose a reciprocal learning approach to jointly optimize a knowledge retriever and a response ranker for knowledge-grounded response retrieval without ground-truth knowledge labels.


Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

1 code implementation NAACL 2022 Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

Such training objective is sub-optimal when the target sequence is not perfect, e. g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available.

Machine Translation Style Transfer +2

SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection

1 code implementation ICCV 2023 Yiran Qin, Chaoqun Wang, Zijian Kang, Ningning Ma, Zhen Li, Ruimao Zhang

In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion and significantly boosts detection performance.

3D Object Detection object-detection

ArSDM: Colonoscopy Images Synthesis with Adaptive Refinement Semantic Diffusion Models

1 code implementation3 Sep 2023 Yuhao Du, Yuncheng Jiang, Shuangyi Tan, Xusheng Wu, Qi Dou, Zhen Li, Guanbin Li, Xiang Wan

Colonoscopy analysis, particularly automatic polyp segmentation and detection, is essential for assisting clinical diagnosis and treatment.

LATR: 3D Lane Detection from Monocular Images with Transformer

1 code implementation ICCV 2023 Yueru Luo, Chaoda Zheng, Xu Yan, Tang Kun, Chao Zheng, Shuguang Cui, Zhen Li

On the one hand, each query is generated based on 2D lane-aware features and adopts a hybrid embedding to enhance lane information.

3D Lane Detection Autonomous Driving

WeakPolyp: You Only Look Bounding Box for Polyp Segmentation

1 code implementation20 Jul 2023 Jun Wei, Yiwen Hu, Shuguang Cui, S. Kevin Zhou, Zhen Li

In contrast, polyp bounding box annotations are much cheaper and more accessible.

SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training

1 code implementation ICCV 2023 Hong Yan, Yang Liu, Yushen Wei, Zhen Li, Guanbin Li, Liang Lin

Moreover, these methods ignore how to utilize the fine-grained dependencies among different skeleton joints to pre-train an efficient skeleton sequence learning model that can generalize well across different datasets.

Action Recognition Representation Learning +1

YONA: You Only Need One Adjacent Reference-frame for Accurate and Fast Video Polyp Detection

no code implementations6 Jun 2023 Yuncheng Jiang, Zixun Zhang, Ruimao Zhang, Guanbin Li, Shuguang Cui, Zhen Li

YONA fully exploits the information of one previous adjacent frame and conducts polyp detection on the current frame without multi-frame collaborations.

Contrastive Learning

SR-OOD: Out-of-Distribution Detection via Sample Repairing

no code implementations26 May 2023 Rui Sun, Andi Zhang, Haiming Zhang, Yao Zhu, Ruimao Zhang, Zhen Li

It is widely reported that deep generative models can classify out-of-distribution (OOD) samples as in-distribution with high confidence.

Out-of-Distribution Detection

Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness

no code implementations25 May 2023 Evgenii Chzhen, Christophe Giraud, Zhen Li, Gilles Stoltz

We consider contextual bandit problems with knapsacks [CBwK], a problem where at each round, a scalar reward is obtained and vector-valued costs are suffered.

Fairness Multi-Armed Bandits

Differential Convolutional Fuzzy Time Series Forecasting

no code implementations15 May 2023 Tianxiang Zhan, Yuanpeng He, Yong Deng, Zhen Li

Thanks to the learnable ability of the neural network, the length of fuzzy rules established in FTSF is expended to an arbitrary length that the expert is not able to handle by the expert system.

Time Series Time Series Forecasting

Hierarchical Weight Averaging for Deep Neural Networks

no code implementations23 Apr 2023 Xiaozhe Gu, Zixun Zhang, Yuncheng Jiang, Tao Luo, Ruimao Zhang, Shuguang Cui, Zhen Li

Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs).

Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation

no code implementations20 Apr 2023 Hao Zhang, Nianwen Si, Yaqi Chen, Wenlin Zhang, Xukui Yang, Dan Qu, Zhen Li

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often requires transcription as extra input during training.

Knowledge Distillation Machine Translation +3

Semantic Human Parsing via Scalable Semantic Transfer over Multiple Label Domains

no code implementations CVPR 2023 Jie Yang, Chaoqun Wang, Zhen Li, Junle Wang, Ruimao Zhang

This paper presents Scalable Semantic Transfer (SST), a novel training paradigm, to explore how to leverage the mutual benefits of the data from different label domains (i. e. various levels of label granularity) to train a powerful human parsing network.

Human Parsing Representation Learning

Fair-CDA: Continuous and Directional Augmentation for Group Fairness

no code implementations1 Apr 2023 Rui Sun, Fengwei Zhou, Zhenhua Dong, Chuanlong Xie, Lanqing Hong, Jiawei Li, Rui Zhang, Zhen Li, Zhenguo Li

By adjusting the perturbation strength in the direction of the paths, our proposed augmentation is controllable and auditable.

Data Augmentation Disentanglement +1

Deep neural operator for learning transient response of interpenetrating phase composites subject to dynamic loading

no code implementations30 Mar 2023 Minglei Lu, Ali Mohammadi, Zhaoxu Meng, Xuhui Meng, Gang Li, Zhen Li

After an offline training, the DNO model can act as surrogate of physics-based FEA to predict the transient mechanical response in terms of reaction force and stress distribution of the IPCs to various strain loads in one second at an accuracy of 98%.

Incremental Learning

An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds

no code implementations21 Mar 2023 Chaoda Zheng, Xu Yan, Haiming Zhang, Baoyuan Wang, Shenghui Cheng, Shuguang Cui, Zhen Li

Due to the motion-centric nature, our method shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training.

3D Single Object Tracking Autonomous Driving +3

SRFormer: Permuted Self-Attention for Single Image Super-Resolution

1 code implementation ICCV 2023 Yupeng Zhou, Zhen Li, Chun-Le Guo, Song Bai, Ming-Ming Cheng, Qibin Hou

Previous works have shown that increasing the window size for Transformer-based image super-resolution models (e. g., SwinIR) can significantly improve the model performance but the computation overhead is also considerable.

Image Super-Resolution

Adaptive Context Selection for Polyp Segmentation

1 code implementation12 Jan 2023 Ruifei Zhang, Guanbin Li, Zhen Li, Shuguang Cui, Dahong Qian, Yizhou Yu

To tackle these issues, we propose an adaptive context selection based encoder-decoder framework which is composed of Local Context Attention (LCA) module, Global Context Module (GCM) and Adaptive Selection Module (ASM).

Benchmarking the Robustness of LiDAR Semantic Segmentation Models

1 code implementation3 Jan 2023 Xu Yan, Chaoda Zheng, Zhen Li, Shuguang Cui, Dengxin Dai

In this paper, we aim to comprehensively analyze the robustness of LiDAR semantic segmentation models under various corruptions.

Autonomous Driving Benchmarking +2

Exploring the Effect of Primitives for Compositional Generalization in Vision-and-Language

no code implementations CVPR 2023 Chuanhao Li, Zhen Li, Chenchen Jing, Yunde Jia, Yuwei Wu

Compositional generalization is critical to simulate the compositional capability of humans, and has received much attention in the vision-and-language (V&L) community.

Question Answering Self-Supervised Learning +2

BEV@DC: Bird's-Eye View Assisted Training for Depth Completion

no code implementations CVPR 2023 Wending Zhou, Xu Yan, Yinghong Liao, Yuankai Lin, Jin Huang, Gangming Zhao, Shuguang Cui, Zhen Li

In practice, the proposed BEV@DC model comprehensively takes advantage of LiDARs with rich geometric details in training, employing an enhanced depth completion manner in inference, which takes only images (RGB and depth) as input.

Autonomous Driving Depth Completion

Learning Transformation-Predictive Representations for Detection and Description of Local Features

no code implementations CVPR 2023 ZiHao Wang, Chunxu Wu, Yifei Yang, Zhen Li

The task of key-points detection and description is to estimate the stable location and discriminative representation of local features, which is essential for image matching.

Contrastive Learning

RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels

no code implementations ICCV 2023 Ziyi Zhang, Weikai Chen, Chaowei Fang, Zhen Li, Lechao Chen, Liang Lin, Guanbin Li

Confidence-wise, we propose a novel sample selection strategy based on confidence representation voting instead of the widely-used small-loss criterion.

Learning with noisy labels Representation Learning +1

DOSnet as a Non-Black-Box PDE Solver: When Deep Learning Meets Operator Splitting

no code implementations11 Dec 2022 Yuan Lan, Zhen Li, Jie Sun, Yang Xiang

Deep neural networks (DNNs) recently emerged as a promising tool for analyzing and solving complex differential equations arising in science and engineering applications.

BoxPolyp:Boost Generalized Polyp Segmentation Using Extra Coarse Bounding Box Annotations

no code implementations7 Dec 2022 Jun Wei, Yiwen Hu, Guanbin Li, Shuguang Cui, S Kevin Zhou, Zhen Li

In practice, box annotations are applied to alleviate the over-fitting issue of previous polyp segmentation models, which generate fine-grained polyp area through the iterative boosted segmentation model.

Geometry-Aware Network for Domain Adaptive Semantic Segmentation

no code implementations2 Dec 2022 Yinghong Liao, Wending Zhou, Xu Yan, Shuguang Cui, Yizhou Yu, Zhen Li

Moreover, to improve the 2D classifier in the target domain, we perform domain-invariant geometric adaptation from source to target and unify the 2D semantic and 3D geometric segmentation results in two domains.

Depth Estimation Depth Prediction +4

Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenes

1 code implementation CVPR 2023 Zhen Li, Lingli Wang, Mofang Cheng, Cihui Pan, Jiaqi Yang

We present a efficient multi-view inverse rendering method for large-scale real-world indoor scenes that reconstructs global illumination and physically-reasonable SVBRDFs.

Inverse Rendering Mixed Reality +2

Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning

2 code implementations12 Nov 2022 Ziyi Zhang, Weikai Chen, Hui Cheng, Zhen Li, Siyuan Li, Liang Lin, Guanbin Li

We investigate a practical domain adaptation task, called source-free domain adaptation (SFUDA), where the source-pretrained model is adapted to the target domain without access to the source data.

Contrastive Learning Source-Free Domain Adaptation

Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

2 code implementations9 Oct 2022 Xu Yan, Heshen Zhan, Chaoda Zheng, Jiantao Gao, Ruimao Zhang, Shuguang Cui, Zhen Li

Specifically, this paper introduces a simple but effective point cloud cross-modality training (PointCMT) strategy, which utilizes view-images, i. e., rendered or projected 2D images of the 3D object, to boost point cloud analysis.

3D Point Cloud Classification Knowledge Distillation +1

Low Error-Rate Approximate Multiplier Design for DNNs with Hardware-Driven Co-Optimization

no code implementations8 Oct 2022 Yao Lu, Jide Zhang, Su Zheng, Zhen Li, Lingli Wang

In this paper, two approximate 3*3 multipliers are proposed and the synthesis results of the ASAP-7nm process library justify that they can reduce the area by 31. 38% and 36. 17%, and the power consumption by 36. 73% and 35. 66% compared with the exact multiplier, respectively.

Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolation

no code implementations7 Oct 2022 Liping Tang, Zhen Li, ZhiQuan Luo, Helen Meng

Further experiments on the downstream task of Cross-Lingual Natural Language Inference show that the proposed model achieves significant performance improvement for distant language pairs in downstream tasks compared to state-of-the-art adversarial and non-adversarial models.

Cross-Lingual Natural Language Inference

Designing An Illumination-Aware Network for Deep Image Relighting

1 code implementation21 Jul 2022 Zuo-Liang Zhu, Zhen Li, Rui-Xun Zhang, Chun-Le Guo, Ming-Ming Cheng

Lighting is a determining factor in photography that affects the style, expression of emotion, and even quality of images.

Image Relighting Image-to-Image Translation

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds

1 code implementation10 Jul 2022 Xu Yan, Jiantao Gao, Chaoda Zheng, Chao Zheng, Ruimao Zhang, Shenghui Cui, Zhen Li

As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion.

Autonomous Driving Knowledge Distillation +3

Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases

no code implementations5 Jul 2022 Zhihao Yuan, Xu Yan, Zhuo Li, Xuhao Li, Yao Guo, Shuguang Cui, Zhen Li

Recent progress in 3D scene understanding has explored visual grounding (3DVG) to localize a target object through a language description.

Representation Learning Scene Understanding +1

Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation Consistency

1 code implementation23 Jun 2022 Weijie Ma, Ye Zhu, Ruimao Zhang, Jie Yang, Yiwen Hu, Zhen Li, Li Xiang

By aligning the class tokens and spatial attention maps of paired NBI and WL images at different levels, the Transformer achieves the ability to keep both global and local representation consistency for the above two modalities.

Classification Image Classification

A Unified Understanding of Deep NLP Models for Text Classification

no code implementations19 Jun 2022 Zhen Li, Xiting Wang, Weikai Yang, Jing Wu, Zhengyan Zhang, Zhiyuan Liu, Maosong Sun, HUI ZHANG, Shixia Liu

The rapid development of deep natural language processing (NLP) models for text classification has led to an urgent need for a unified understanding of these models proposed individually.

text-classification Text Classification

AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation

1 code implementation16 Jun 2022 Yuanfeng Ji, Haotian Bai, Jie Yang, Chongjian Ge, Ye Zhu, Ruimao Zhang, Zhen Li, Lingyan Zhang, Wanling Ma, Xiang Wan, Ping Luo

Constraint by the high cost of collecting and labeling 3D medical data, most of the deep learning models to date are driven by datasets with a limited number of organs of interest or samples, which still limits the power of modern deep models and makes it difficult to provide a fully comprehensive and fair estimate of various methods.

Image Segmentation Medical Image Segmentation +2

Universality and approximation bounds for echo state networks with random weights

no code implementations12 Jun 2022 Zhen Li, Yunfei Yang

We study the uniform approximation of echo state networks with randomly generated internal weights.

Contextual Bandits with Knapsacks for a Conversion Model

no code implementations1 Jun 2022 Zhen Li, Gilles Stoltz

At each round, given the stochastic i. i. d.\ context $\mathbf{x}_t$ and the arm picked $a_t$ (corresponding, e. g., to a discount level), a customer conversion may be obtained, in which case a reward $r(a,\mathbf{x}_t)$ is gained and vector costs $c(a_t,\mathbf{x}_t)$ are suffered (corresponding, e. g., to losses of earnings).

Multi-Armed Bandits

6GAN: IPv6 Multi-Pattern Target Generation via Generative Adversarial Nets with Reinforcement Learning

1 code implementation21 Apr 2022 Tianyu Cui, Gaopeng Gou, Gang Xiong, Chang Liu, Peipei Fu, Zhen Li

6GAN forces multiple generators to train with a multi-class discriminator and an alias detector to generate non-aliased active targets with different addressing pattern types.

Decision Making reinforcement-learning +1

Towards An End-to-End Framework for Flow-Guided Video Inpainting

2 code implementations CVPR 2022 Zhen Li, Cheng-Ze Lu, Jianhua Qin, Chun-Le Guo, Ming-Ming Cheng

Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories.

Optical Flow Estimation Seeing Beyond the Visible +1

Graph Enhanced Contrastive Learning for Radiology Findings Summarization

1 code implementation ACL 2022 Jinpeng Hu, Zhuo Li, Zhihong Chen, Zhen Li, Xiang Wan, Tsung-Hui Chang

To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i. e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation.

Contrastive Learning

ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification

1 code implementation13 Feb 2022 Xinjie Lin, Gang Xiong, Gaopeng Gou, Zhen Li, Junzheng Shi, Jing Yu

In this paper, we propose a new traffic representation model called Encrypted Traffic Bidirectional Encoder Representations from Transformer (ET-BERT), which pre-trains deep contextualized datagram-level representation from large-scale unlabeled data.

Classification Management +1

RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation

1 code implementation12 Feb 2022 Zhen Li, Guenevere, Chen, Chen Chen, Yayi Zou, Shouhuai Xu

Recent studies show that current source code authorship attribution methods can be compromised by attackers exploiting adversarial examples and coding style manipulation.

Data Augmentation

HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks

2 code implementations20 Jan 2022 Su Zheng, Zhen Li, Yao Lu, Jingbo Gao, Jide Zhang, Lingli Wang

We propose an optimization method for the automatic design of approximate multipliers, which minimizes the average error according to the operand distributions.

Quantization Vocal Bursts Intensity Prediction

Heuristic Search for Rank Aggregation with Application to Label Ranking

no code implementations11 Jan 2022 Yangming Zhou, Jin-Kao Hao, Zhen Li, Fred Glover

Rank aggregation aims to combine the preference rankings of a number of alternatives from different voters into a single consensus ranking.

PhyIR: Physics-Based Inverse Rendering for Panoramic Indoor Images

1 code implementation CVPR 2022 Zhen Li, Lingli Wang, Xiang Huang, Cihui Pan, Jiaqi Yang

In this paper, we present PhyIR, a neural inverse rendering method with a more completed SVBRDF representation and a physics-based in-network rendering layer, which can handle complex material and incorporate physical constraints by re-rendering realistic and detailed specular reflectance.

Inverse Rendering

CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization

no code implementations2 Dec 2021 Wei Liu, Huanqin Wu, Wenjing Mu, Zhen Li, Tao Chen, Dan Nie

We propose CO2Sum (Contrastive for Consistency), a contrastive learning scheme that can be easily applied on sequence-to-sequence models for factual-consistent abstractive summarization, proving that the model can be fact-aware without modifying the architecture.

Abstractive Text Summarization Contrastive Learning

Active Learning for Event Extraction with Memory-based Loss Prediction Model

no code implementations26 Nov 2021 Shirong Shen, Zhen Li, Guilin Qi

During the selection process, we use an internal-external sample loss ranking method to evaluate the sample importance by using local information.

Active Learning Event Extraction

Rapid Assessments of Light-Duty Gasoline Vehicle Emissions Using On-Road Remote Sensing and Machine Learning

no code implementations1 Oct 2021 Yan Xia, Linhui Jiang, Lu Wang, Xue Chen, Jianjie Ye, Tangyan Hou, Liqiang Wang, Yibo Zhang, Mengying Li, Zhen Li, Zhe Song, Yaping Jiang, Weiping Liu, Pengfei Li, Daniel Rosenfeld, John H. Seinfeld, Shaocai Yu

Our results show that the ORRS measurements, assisted by the machine-learning-based ensemble model developed here, can realize day-to-day supervision of on-road vehicle-specific emissions.

Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds

2 code implementations ICCV 2021 Chaoda Zheng, Xu Yan, Jiantao Gao, Weibing Zhao, Wei zhang, Zhen Li, Shuguang Cui

Current 3D single object tracking approaches track the target based on a feature comparison between the target template and the search area.

3D Single Object Tracking Object Tracking

Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment

no code implementations5 Aug 2021 Qin Wang, Hui Che, Weizhen Ding, Li Xiang, Guanbin Li, Zhen Li, Shuguang Cui

Thus, we propose a novel framework based on a teacher-student architecture for the accurate colorectal polyp classification (CPC) through directly using white-light (WL) colonoscopy images in the examination.

Contrastive Learning

Towards Making Deep Learning-based Vulnerability Detectors Robust

1 code implementation2 Aug 2021 Zhen Li, Jing Tang, Deqing Zou, Qian Chen, Shouhuai Xu, Chao Zhang, Yichen Li, Hai Jin

Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.

Shallow Feature Matters for Weakly Supervised Object Localization

1 code implementation CVPR 2021 Jun Wei, Qin Wang, Zhen Li, Sheng Wang, S. Kevin Zhou, Shuguang Cui

In practice, our SPOL model first generates the CAMs through a novel element-wise multiplication of shallow and deep feature maps, which filters the background noise and generates sharper boundaries robustly.

Pseudo Label Weakly-Supervised Object Localization

Inverse Problem of Nonlinear Schrödinger Equation as Learning of Convolutional Neural Network

no code implementations19 Jul 2021 Yiran Wang, Zhen Li

In this work, we use an explainable convolutional neural network (NLS-Net) to solve an inverse problem of the nonlinear Schr\"odinger equation, which is widely used in fiber-optic communications.

Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generation

1 code implementation29 Jun 2021 Guangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao, Zhen Li, Xiaodong He, Shuguang Cui, Zhiting Hu

Such training objective is sub-optimal when the target sequence is not perfect, e. g., when the target sequence is corrupted with noises, or when only weak sequence supervision is available.

Machine Translation Style Transfer +3

Multi-Compound Transformer for Accurate Biomedical Image Segmentation

1 code implementation28 Jun 2021 Yuanfeng Ji, Ruimao Zhang, Huijie Wang, Zhen Li, Lingyun Wu, Shaoting Zhang, Ping Luo

The recent vision transformer(i. e. for image classification) learns non-local attentive interaction of different patch tokens.

Image Classification Image Segmentation +2

An error analysis of generative adversarial networks for learning distributions

no code implementations27 May 2021 Jian Huang, Yuling Jiao, Zhen Li, Shiao Liu, Yang Wang, Yunfei Yang

This paper studies how well generative adversarial networks (GANs) learn probability distributions from finite samples.

CARLS: Cross-platform Asynchronous Representation Learning System

1 code implementation26 May 2021 Chun-Ta Lu, Yun Zeng, Da-Cheng Juan, Yicheng Fan, Zhe Li, Jan Dlabal, Yi-Ting Chen, Arjun Gopalan, Allan Heydon, Chun-Sung Ferng, Reah Miyara, Ariel Fuxman, Futang Peng, Zhen Li, Tom Duerig, Andrew Tomkins

In this work, we propose CARLS, a novel framework for augmenting the capacity of existing deep learning frameworks by enabling multiple components -- model trainers, knowledge makers and knowledge banks -- to concertedly work together in an asynchronous fashion across hardware platforms.

Representation Learning

Combining Supervised and Un-supervised Learning for Automatic Citrus Segmentation

no code implementations4 May 2021 Heqing Huang, Tongbin Huang, Zhen Li, Zhiwei Wei, Shilei Lv

Compared with most of the existing citrus segmentation methods, our method uses a small amount of supervised data and a large number of unsupervised data, while learning the pixel level location information and the temporal information of citrus changes to enhance the segmentation effect.

Image Segmentation Semantic Segmentation

PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery

1 code implementation30 Apr 2021 Weibing Zhao, Xu Yan, Jiantao Gao, Ruimao Zhang, Jiayan Zhang, Zhen Li, Song Wu, Shuguang Cui

In this paper, we address a fundamental problem in PCSR: How to downsample the dense point cloud with arbitrary scales while preserving the local topology of discarding points in a case-agnostic manner (i. e. without additional storage for point relationship)?

Temporal Modulation Network for Controllable Space-Time Video Super-Resolution

1 code implementation CVPR 2021 Gang Xu, Jun Xu, Zhen Li, Liang Wang, Xing Sun, Ming-Ming Cheng

To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos.

Space-time Video Super-resolution Video Super-Resolution

Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud

1 code implementation ICCV 2021 Mingtao Feng, Zhen Li, Qi Li, Liang Zhang, Xiangdong Zhang, Guangming Zhu, HUI ZHANG, Yaonan Wang, Ajmal Mian

There are three main challenges in 3D object grounding: to find the main focus in the complex and diverse description; to understand the point cloud scene; and to locate the target object.

Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision

4 code implementations11 Feb 2021 Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, YunHsuan Sung, Zhen Li, Tom Duerig

In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset.

 Ranked #1 on Image Classification on VTAB-1k (using extra training data)

Cross-Modal Retrieval Fine-Grained Image Classification +6

On the capacity of deep generative networks for approximating distributions

no code implementations29 Jan 2021 Yunfei Yang, Zhen Li, Yang Wang

Furthermore, it is shown that the approximation error in Wasserstein distance grows at most linearly on the ambient dimension and that the approximation order only depends on the intrinsic dimension of the target distribution.

GAKP: GRU Association and Kalman Prediction for Multiple Object Tracking

no code implementations28 Dec 2020 Zhen Li, Sunzeng Cai, Xiaoyi Wang, Zhe Liu, Nian Xue

Multiple Object Tracking (MOT) has been a useful yet challenging task in many real-world applications such as video surveillance, intelligent retail, and smart city.

Multiple Object Tracking

Formal modeling and performance evaluation for hybrid systems:a probabilistic hybrid process algebra-based approach

no code implementations23 Dec 2020 Fujun Wang, Zining Cao, Lixing Tan, Zhen Li

After that, we present a performance evaluation language, CTRML, to reason over probabilistic systems, which extend the results to real number.

Formal Languages and Automata Theory F.4.3

Operator learning for predicting multiscale bubble growth dynamics

no code implementations23 Dec 2020 Chensen Lin, Zhen Li, Lu Lu, Shengze Cai, Martin Maxey, George Em Karniadakis

Simulating and predicting multiscale problems that couple multiple physics and dynamics across many orders of spatiotemporal scales is a great challenge that has not been investigated systematically by deep neural networks (DNNs).

Computational Physics

Hierarchically nanostructured thermoelectric materials: Challenges and opportunities for improved power factors

no code implementations22 Dec 2020 Neophytos Neophytou, Vassilios Vargiamidis, Samuel Foster, Patrizio Graziosi, Laura de Sousa Oliveira, Dhritiman Chakraborty, Zhen Li, Mischa Thesberg, Hans Kosina, Nick Bennett, Giovanni Pennelli, Dario Narducci

Central to this ZT improvement is the drastic reduction in the material thermal conductivity due to the scattering of phonons on the numerous interfaces, boundaries, dislocations, point defects, phases, etc., which are purposely included.

Materials Science

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

2 code implementations7 Dec 2020 Xu Yan, Jiantao Gao, Jie Li, Ruimao Zhang, Zhen Li, Rui Huang, Shuguang Cui

In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.

3D Semantic Scene Completion from a single RGB image 3D Semantic Segmentation +2

DeepSIM: GPS Spoofing Detection on UAVs using Satellite Imagery Matching

1 code implementation1 Dec 2020 Nian Xue, Liang Niu, Xianbin Hong, Zhen Li, Larissa Hoffaeller, Christina Pöpper

To detect GPS spoofing attacks, we investigate different deep neural network models that compare the real-time camera images with the historical satellite images.

Delving Deep into Label Smoothing

2 code implementations25 Nov 2020 Chang-Bin Zhang, Peng-Tao Jiang, Qibin Hou, Yunchao Wei, Qi Han, Zhen Li, Ming-Ming Cheng

Experiments demonstrate that based on the same classification models, the proposed approach can effectively improve the classification performance on CIFAR-100, ImageNet, and fine-grained datasets.

Classification General Classification

Multi-Modal Active Learning for Automatic Liver Fibrosis Diagnosis based on Ultrasound Shear Wave Elastography

no code implementations2 Nov 2020 Lufei Gao, Ruisong Zhou, Changfeng Dong, Cheng Feng, Zhen Li, Xiang Wan, Li Liu

With the development of radiomics, noninvasive diagnosis like ultrasound (US) imaging plays a very important role in automatic liver fibrosis diagnosis (ALFD).

Active Learning

UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation

no code implementations16 Sep 2020 Yuanfeng Ji, Ruimao Zhang, Zhen Li, Jiamin Ren, Shaoting Zhang, Ping Luo

Unlike the recent neural architecture search (NAS) methods that typically searched the optimal operators in each network layer, but missed a good strategy to search for feature aggregations, this paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network.

Image Segmentation Neural Architecture Search +2

Ultrasound Liver Fibrosis Diagnosis using Multi-indicator guided Deep Neural Networks

no code implementations10 Sep 2020 Jiali Liu, Wenxuan Wang, Tianyao Guan, Ningbo Zhao, Xiaoguang Han, Zhen Li

An indicator-guided learning mechanism is further proposed to ease the training of the proposed model.

Diagnosing Concept Drift with Visual Analytics

no code implementations28 Jul 2020 Weikai Yang, Zhen Li, Mengchen Liu, Yafeng Lu, Kelei Cao, Ross Maciejewski, Shixia Liu

Concept drift is a phenomenon in which the distribution of a data stream changes over time in unforeseen ways, causing prediction models built on historical data to become inaccurate.

text-classification Text Classification

IllumiNet: Transferring Illumination from Planar Surfaces to Virtual Objects in Augmented Reality

no code implementations12 Jul 2020 Di Xu, Zhen Li, Yanning Zhang, Qi Cao

This paper presents an illumination estimation method for virtual objects in real environment by learning.

Interactive Knowledge Distillation

no code implementations3 Jul 2020 Shipeng Fu, Zhen Li, Jun Xu, Ming-Ming Cheng, Zitao Liu, Xiaomin Yang

Knowledge distillation is a standard teacher-student learning framework to train a light-weight student network under the guidance of a well-trained large teacher network.

Image Classification Knowledge Distillation

A Robust Attentional Framework for License Plate Recognition in the Wild

no code implementations6 Jun 2020 Linjiang Zhang, Peng Wang, Hui Li, Zhen Li, Chunhua Shen, Yanning Zhang

On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly.

Image Generation License Plate Recognition

Approximation in shift-invariant spaces with deep ReLU neural networks

no code implementations25 May 2020 Yunfei Yang, Zhen Li, Yang Wang

We also give lower bounds of the $L^p (1\le p \le \infty)$ approximation error for Sobolev spaces, which show that our construction of neural network is asymptotically optimal up to a logarithmic factor.

Exemplar Normalization for Learning Deep Representation

no code implementations CVPR 2020 Ruimao Zhang, Zhanglin Peng, Lingyun Wu, Zhen Li, Ping Luo

This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn different normalization methods for different convolutional layers and image samples of a deep network.

Semantic Segmentation

PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling

1 code implementation CVPR 2020 Xu Yan, Chaoda Zheng, Zhen Li, Sheng Wang, Shuguang Cui

Extensive experiments verify the robustness and superiority of our approach in point clouds processing tasks regardless of synthesis data, indoor data, and outdoor data with or without noise.

3D Point Cloud Classification Semantic Segmentation

Automated classification of stems and leaves of potted plants based on point cloud data

no code implementations28 Feb 2020 Zichu Liu, Qing Zhang, Pei Wang, Zhen Li, Huiru Wang

A classification method was proposed to classify the leaves and stems of potted plants automatically based on the point cloud data of the plants, which is a nondestructive acquisition.

General Classification

BARNet: Bilinear Attention Network with Adaptive Receptive Fields for Surgical Instrument Segmentation

no code implementations20 Jan 2020 Zhen-Liang Ni, Gui-Bin Bian, Guan-An Wang, Xiao-Hu Zhou, Zeng-Guang Hou, Xiao-Liang Xie, Zhen Li, Yu-Han Wang

For the scale variation, our adaptive receptive field module aggregates multi-scale features and automatically fuses them with different weights.

Semantic Segmentation

$μ$VulDeePecker: A Deep Learning-Based System for Multiclass Vulnerability Detection

no code implementations8 Jan 2020 Deqing Zou, Sujuan Wang, Shouhuai Xu, Zhen Li, Hai Jin

Existing vulnerability detection methods based on deep learning can detect the presence of vulnerabilities (i. e., addressing the binary classification or detection problem), but cannot pinpoint types of vulnerabilities (i. e., incapable of addressing multiclass classification).

Binary Classification General Classification +1

Attention-Guided Lightweight Network for Real-Time Segmentation of Robotic Surgical Instruments

1 code implementation24 Oct 2019 Zhen-Liang Ni, Gui-Bin Bian, Zeng-Guang Hou, Xiao-Hu Zhou, Xiao-Liang Xie, Zhen Li

LWANet adopts encoder-decoder architecture, where the encoder is the lightweight network MobileNetV2, and the decoder consists of depthwise separable convolution, attention fusion block, and transposed convolution.

PPINN: Parareal Physics-Informed Neural Network for time-dependent PDEs

no code implementations23 Sep 2019 Xuhui Meng, Zhen Li, Dongkun Zhang, George Em. Karniadakis

Consequently, compared to the original PINN approach, the proposed PPINN approach may achieve a significant speedup for long-time integration of PDEs, assuming that the CG solver is fast and can provide reasonable predictions of the solution, hence aiding the PPINN solution to converge in just a few iterations.

Small Data Image Classification

Semi-Supervised Video Salient Object Detection Using Pseudo-Labels

1 code implementation ICCV 2019 Pengxiang Yan, Guanbin Li, Yuan Xie, Zhen Li, Chuan Wang, Tianshui Chen, Liang Lin

Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.

 Ranked #1 on Video Salient Object Detection on VOS-T (using extra training data)

object-detection Salient Object Detection +2

Convergence Rates of Posterior Distributions in Markov Decision Process

no code implementations22 Jul 2019 Zhen Li, Eric Laber

In this paper, we show the convergence rates of posterior distributions of the model dynamics in a MDP for both episodic and continuous tasks.

Thompson Sampling

Gated Multiple Feedback Network for Image Super-Resolution

1 code implementation9 Jul 2019 Qilei Li, Zhen Li, Lu Lu, Gwanggil Jeon, Kai Liu, Xiaomin Yang

The rapid development of deep learning (DL) has driven single image super-resolution (SR) into a new era.

Image Super-Resolution

Influence of Boundaries and Thermostatting on Nonequilibrium Molecular Dynamics Simulations of Heat Conduction in Solids

no code implementations27 May 2019 Zhen Li, Shiyun Xiong, Charles Sievers, Yue Hu, Zheyong Fan, Ning Wei, Hua Bao, Shunda Chen, Davide Donadio, Tapio Ala-Nissila

Conventionally, the thermal conductivity of a finite system is calculated as the ratio between the heat flux and the temperature gradient extracted from the linear part of the temperature profile away from the local thermostats.

Mesoscale and Nanoscale Physics Statistical Mechanics Computational Physics

Efficient hinging hyperplanes neural network and its application in nonlinear system identification

no code implementations15 May 2019 Jun Xu, Qinghua Tao, Zhen Li, Xiangming Xi, Johan A. K. Suykens, Shuning Wang

It is proved that for every EHH neural network, there is an equivalent adaptive hinging hyperplanes (AHH) tree, which was also proposed based on the model of HH and find good applications in system identification.

regression Variable Selection

A GPU-accelerated package for simulation of flow in nanoporous source rocks with many-body dissipative particle dynamics

2 code implementations25 Mar 2019 Yidong Xia, Ansel Blumers, Zhen Li, Lixiang Luo, Yu-Hang Tang, Joshua Kane, Hai Huang, Matthew Andrew, Milind Deo, Jan Goral

Lastly, we demonstrate, through a flow simulation in realistic shale pores, that the CPU counterpart requires 840 Power9 cores to rival the performance delivered by our package with four V100 GPUs on ORNL's Summit architecture.

Computational Physics

Feedback Network for Image Super-Resolution

4 code implementations CVPR 2019 Zhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu

In this paper, we propose an image super-resolution feedback network (SRFBN) to refine low-level representations with high-level information.

Image Super-Resolution

Graph-RISE: Graph-Regularized Image Semantic Embedding

1 code implementation14 Feb 2019 Da-Cheng Juan, Chun-Ta Lu, Zhen Li, Futang Peng, Aleksei Timofeev, Yi-Ting Chen, Yaxi Gao, Tom Duerig, Andrew Tomkins, Sujith Ravi

Learning image representations to capture fine-grained semantics has been a challenging and important task enabling many applications such as image search and clustering.

Clustering General Classification +4

Thompson Sampling for Pursuit-Evasion Problems

no code implementations11 Nov 2018 Zhen Li, Nicholas J. Meyer, Eric B. Laber, Robert Brigantic

We propose a variant of Thompson Sampling for pursuit-evasion that allows for the application of existing model-based planning algorithms.

Thompson Sampling

Nonlocal flocking dynamics: Learning the fractional order of PDEs from particle simulations

no code implementations27 Oct 2018 Zhiping Mao, Zhen Li, George Em. Karniadakis

Instead of specifying the fPDEs with an ad hoc fractional order for nonlocal flocking dynamics, we learn the effective nonlocal influence function in fPDEs directly from particle trajectories generated by the agent-based simulations.

Bayesian Optimization

Multivariate Density Estimation with Missing Data

1 code implementation14 Aug 2018 Zhen Li, Lili Wu, Weilian Zhou, Sujit Ghosh

Multivariate density estimation is a popular technique in statistics with wide applications including regression models allowing for heteroskedasticity in conditional variances.


SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities

4 code implementations18 Jul 2018 Zhen Li, Deqing Zou, Shouhuai Xu, Hai Jin, Yawei Zhu, Zhaoxuan Chen

Our experiments with 4 software products demonstrate the usefulness of the framework: we detect 15 vulnerabilities that are not reported in the National Vulnerability Database.

Vulnerability Detection

Deep Neural Nets with Interpolating Function as Output Activation

1 code implementation NeurIPS 2018 Bao Wang, Xiyang Luo, Zhen Li, Wei Zhu, Zuoqiang Shi, Stanley J. Osher

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function.

VulDeePecker: A Deep Learning-Based System for Vulnerability Detection

4 code implementations5 Jan 2018 Zhen Li, Deqing Zou, Shouhuai Xu, Xinyu Ou, Hai Jin, Sujuan Wang, Zhijun Deng, Yuyi Zhong

Since deep learning is motivated to deal with problems that are very different from the problem of vulnerability detection, we need some guiding principles for applying deep learning to vulnerability detection.

Vulnerability Detection

Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN

no code implementations21 Nov 2017 Jiyang Gao, Zijian, Guo, Zhen Li, Ram Nevatia

To address these challenges, we propose a Knowledge Concentration method, which effectively transfers the knowledge from dozens of specialists (multiple teacher networks) into one single model (one student network) to classify 100K object categories.

General Classification Image Classification +1

Understanding Hidden Memories of Recurrent Neural Networks

1 code implementation30 Oct 2017 Yao Ming, Shaozu Cao, Ruixiang Zhang, Zhen Li, Yuanzhe Chen, Yangqiu Song, Huamin Qu

We propose a technique to explain the function of individual hidden state units based on their expected response to input texts.


High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

no code implementations ICCV 2017 Xiaoguang Han, Zhen Li, Haibin Huang, Evangelos Kalogerakis, Yizhou Yu

Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network.

Folding membrane proteins by deep transfer learning

no code implementations28 Aug 2017 Sheng Wang, Zhen Li, Yizhou Yu, Jinbo Xu

Computational elucidation of membrane protein (MP) structures is challenging partially due to lack of sufficient solved structures for homology modeling.

Transfer Learning

A Flow Model of Neural Networks

no code implementations21 Aug 2017 Zhen Li, Zuoqiang Shi

Based on a natural connection between ResNet and transport equation or its characteristic equation, we propose a continuous flow model for both ResNet and plain net.

Learning Gaussian Graphical Models Using Discriminated Hub Graphical Lasso

no code implementations17 May 2017 Zhen Li, Jingtian Bai, Weilian Zhou

When no hubs are known, we use Graphical Lasso (GL) to provide information of hubs and find that the performance of DHGL will always be better than HGL if correct prior information is given and will seldom degenerate when the prior information is wrong.

Predicting membrane protein contacts from non-membrane proteins by deep transfer learning

no code implementations24 Apr 2017 Zhen Li, Sheng Wang, Yizhou Yu, Jinbo Xu

Tested on 510 non-redundant MPs, our deep model (learned from only non-MPs) has top L/10 long-range contact prediction accuracy 0. 69, better than our deep model trained by only MPs (0. 63) and much better than a representative DCA method CCMpred (0. 47) and the CASP11 winner MetaPSICOV (0. 55).

Transfer Learning

GPU-accelerated Red Blood Cells Simulations with Transport Dissipative Particle Dynamics

2 code implementations18 Nov 2016 Ansel L. Blumers, Yu-Hang Tang, Zhen Li, Xuejin Li, George E. Karniadakis

We observe a speedup of 10. 1 on one GPU over all 16 cores within a single node, and a weak scaling efficiency of 91% across 256 nodes.

Computational Physics Biological Physics

Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

1 code implementation2 Sep 2016 Sheng Wang, Siqi Sun, Zhen Li, Renyu Zhang, Jinbo Xu

Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0. 5.

Protein Folding

Protein Secondary Structure Prediction Using Cascaded Convolutional and Recurrent Neural Networks

1 code implementation25 Apr 2016 Zhen Li, Yizhou Yu

Inspired by the recent successes of deep neural networks, in this paper, we propose an end-to-end deep network that predicts protein secondary structures from integrated local and global contextual features.

Multi-Task Learning Protein Secondary Structure Prediction

Towards Better Analysis of Deep Convolutional Neural Networks

no code implementations24 Apr 2016 Mengchen Liu, Jiaxin Shi, Zhen Li, Chongxuan Li, Jun Zhu, Shixia Liu

Deep convolutional neural networks (CNNs) have achieved breakthrough performance in many pattern recognition tasks such as image classification.

Image Classification

LSTM-CF: Unifying Context Modeling and Fusion with LSTMs for RGB-D Scene Labeling

1 code implementation18 Apr 2016 Zhen Li, Yukang Gan, Xiaodan Liang, Yizhou Yu, Hui Cheng, Liang Lin

Another long short-term memorized fusion layer is set up to integrate the contexts along the vertical direction from different channels, and perform bi-directional propagation of the fused vertical contexts along the horizontal direction to obtain true 2D global contexts.

Scene Labeling

Blockout: Dynamic Model Selection for Hierarchical Deep Networks

no code implementations CVPR 2016 Calvin Murdock, Zhen Li, Howard Zhou, Tom Duerig

Most deep architectures for image classification--even those that are trained to classify a large number of diverse categories--learn shared image representations with a single model.

Clustering General Classification +2

Learning Locally-Adaptive Decision Functions for Person Verification

no code implementations CVPR 2013 Zhen Li, Shiyu Chang, Feng Liang, Thomas S. Huang, Liangliang Cao, John R. Smith

This paper proposes to learn a decision function for verification that can be viewed as a joint model of a distance metric and a locally adaptive thresholding rule.

Face Verification Metric Learning +2

Learning to Search Efficiently in High Dimensions

no code implementations NeurIPS 2011 Zhen Li, Huazhong Ning, Liangliang Cao, Tong Zhang, Yihong Gong, Thomas S. Huang

Traditional approaches relied on algorithmic constructions that are often data independent (such as Locality Sensitive Hashing) or weakly dependent (such as kd-trees, k-means trees).

Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.