Search Results for author: Yu Li

Found 116 papers, 54 papers with code

基于层次化语义框架的知识库属性映射方法(Property Mapping in Knowledge Base Under the Hierarchical Semantic Framework)

no code implementations CCL 2020 Yu Li, Guangyou Zhou

面向知识库的自动问答是自然语言处理的一项重要任务, 它旨在对用户提出的自然语言形式问题给出精炼、准确的回复。目前由于缺少数据集、特征不一致等因素, 导致难以使用通用的数据和方法实现领域知识库问答。因此, 本文将“问题意图”视作不同领域问答可能存在的共同特征, 将“问题”与三元组知识库中“关系谓词”的映射过程作为问答核心工作。为了考虑多种层次的语义避免重要信息的损失, 本文分别将“基于门控卷积的深层语义”和“基于交互注意力机制的浅层语义”两个方面通过门控感知机制相融合。我们在NLPCC-ICCPOL 2016 KBQA数据集上的实验表明, 本文提出的方法与现有的基于CDSSM和BDSSM相比, 效能有明显的提升。此外, 本文通过构造天文常识知识库, 将问题与关系谓词映射模型移植到特定领域, 结合Bi-LSTM-CRF模型构建了天文常识自动问答系统。

Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-Information

no code implementations Findings (NAACL) 2022 Bowen Yang, Cong Han, Yu Li, Lei Zuo, Zhou Yu

In this paper, we propose a simple yet effective architecture comprising a pre-trained language model (PLM) and an item metadata encoder to integrate the recommendation and the dialog generation better.

Knowledge Graphs Language Modelling +2

An Empirical Study on the Efficacy of Deep Active Learning for Image Classification

no code implementations30 Nov 2022 Yu Li, Muxi Chen, Yannan Liu, Daojing He, Qiang Xu

Third, performing data selection in the SSAL setting can achieve a significant and consistent performance improvement, especially with abundant unlabeled data.

Learning Single Image Defocus Deblurring with Misaligned Training Pairs

1 code implementation26 Nov 2022 Yu Li, Dongwei Ren, Xinya Shu, WangMeng Zuo

First, in the deblurring module, a bi-directional optical flow-based deformation is introduced to tolerate spatial misalignment between deblurred and ground-truth images.

Deblurring Image Defocus Deblurring +1

Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems

1 code implementation22 Oct 2022 David Gros, Yu Li, Zhou Yu

Dialog systems are often designed or trained to output human-like responses.

Robust Human Matting via Semantic Guidance

1 code implementation11 Oct 2022 Xiangguang Chen, Ye Zhu, Yu Li, Bingtao Fu, Lei Sun, Ying Shan, Shan Liu

Unlike previous works, our framework is data efficient, which requires a small amount of matting ground-truth to learn to estimate high quality object mattes.

Image Matting

GTAV-NightRain: Photometric Realistic Large-scale Dataset for Night-time Rain Streak Removal

no code implementations10 Oct 2022 Fan Zhang, ShaoDi You, Yu Li, Ying Fu

In this paper, we propose GTAV-NightRain dataset, which is a large-scale synthetic night-time rain streak removal dataset.

Rethinking Knowledge Distillation via Cross-Entropy

1 code implementation22 Aug 2022 Zhendong Yang, Zhe Li, Yuan Gong, Tianke Zhang, Shanshan Lao, Chun Yuan, Yu Li

Furthermore, we smooth students' target output to treat it as the soft target for training without teachers and propose a teacher-free new KD loss (tf-NKD).

Knowledge Distillation

Genome-wide nucleotide-resolution model of single-strand break site reveals species evolutionary hierarchy

1 code implementation21 Aug 2022 Sheng Xu, Junkang Wei, Yu Li

Besides, SSBlazer is a lightweight model with robust cross-species generalization ability in the cross-species evaluation, which enables the large-scale genome-wide application in diverse species.

Deep Learning-enabled Spatial Phase Unwrapping for 3D Measurement

1 code implementation6 Aug 2022 Xiaolong Luo, Wanzhong Song, Songlin Bai, Yu Li, Zhihe Zhao

This system necessitates a robust spatial phase unwrapping (SPU) algorithm.

Using Chatbots to Teach Languages

no code implementations31 Jul 2022 Yu Li, Chun-Yen Chen, Dian Yu, Sam Davidson, Ryan Hou, Xun Yuan, Yinghua Tan, Derek Pham, Zhou Yu

This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners.

reinforcement-learning

A Multi-tasking Model of Speaker-Keyword Classification for Keeping Human in the Loop of Drone-assisted Inspection

1 code implementation8 Jul 2022 Yu Li, Anisha Parsan, Bill Wang, Penghao Dong, Shanshan Yao, Ruwen Qin

A base model for a group of five authorized subjects is trained and tested on the inspection keyword dataset collected by this study.

E2Efold-3D: End-to-End Deep Learning Method for accurate de novo RNA 3D Structure Prediction

1 code implementation4 Jul 2022 Tao Shen, Zhihang Hu, Zhangzhi Peng, Jiayang Chen, Peng Xiong, Liang Hong, Liangzhen Zheng, YiXuan Wang, Irwin King, Sheng Wang, Siqi Sun, Yu Li

When E2Efold-3D is coupled with the experimental techniques, the RNA structure prediction field can be greatly advanced.

Do we really need temporal convolutions in action segmentation?

no code implementations26 May 2022 Dazhao Du, Bing Su, Yu Li, Zhongang Qi, Lingyu Si, Ying Shan

Most state-of-the-art methods focus on designing temporal convolution-based models, but the inflexibility of temporal convolutions and the difficulties in modeling long-term temporal dependencies restrict the potential of these models.

Action Classification Action Segmentation +1

ProNet DB: A proteome-wise database for protein surface property representations and RNA-binding profiles

no code implementations16 May 2022 Junkang Wei, Jin Xiao, Siyuan Chen, Licheng Zong, Xin Gao, Yu Li

The rapid growth in the number of experimental and predicted protein structures and more complicated protein structures challenge users in computational biology for utilizing the structural information and protein surface property representation.

Drug Discovery

Learning Dual-Pixel Alignment for Defocus Deblurring

1 code implementation26 Apr 2022 Yu Li, Yaling Yi, Dongwei Ren, Qince Li, WangMeng Zuo

Generally, DPANet is an encoder-decoder with skip-connections, where two branches with shared parameters in the encoder are employed to extract and align deep features from left and right views, and one decoder is adopted to fuse aligned features for predicting the all-in-focus image.

Deblurring

"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs

1 code implementation25 Apr 2022 Shuo Zhang, Junzhou Zhao, Pinghui Wang, Yu Li, Yi Huang, Junlan Feng

Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses.

Multi-Task Learning

Temporally Efficient Vision Transformer for Video Instance Segmentation

2 code implementations CVPR 2022 Shusheng Yang, Xinggang Wang, Yu Li, Yuxin Fang, Jiemin Fang, Wenyu Liu, Xun Zhao, Ying Shan

To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS).

Instance Segmentation Semantic Segmentation +1

Interpretable RNA Foundation Model from Unannotated Data for Highly Accurate RNA Structure and Function Predictions

1 code implementation1 Apr 2022 Jiayang Chen, Zhihang Hu, Siqi Sun, Qingxiong Tan, YiXuan Wang, Qinze Yu, Licheng Zong, Liang Hong, Jin Xiao, Tao Shen, Irwin King, Yu Li

Non-coding RNA structure and function are essential to understanding various biological processes, such as cell signaling, gene expression, and post-transcriptional regulations.

Self-Supervised Learning

A physics and data co-driven surrogate modeling approach for temperature field prediction on irregular geometric domain

no code implementations15 Mar 2022 Kairui Bao, Wen Yao, Xiaoya Zhang, Wei Peng, Yu Li

Second, a physics-driven CNN surrogate with partial differential equation (PDE) residuals as a loss function is utilized for fast meshing (meshing surrogate); then, we present a data-driven surrogate model based on the multi-level reduced-order method, aiming to learn solutions of temperature field in the above regular computational plane (thermal surrogate).

SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representations

no code implementations15 Feb 2022 Tao Wang, Jun Hao Liew, Yu Li, Yunpeng Chen, Jiashi Feng

Unlike the original per grid cell object masks, SODAR is implicitly supervised to learn mask representations that encode geometric structure of nearby objects and complement adjacent representations with context.

Instance Segmentation Semantic Segmentation

Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval

1 code implementation24 Jan 2022 Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan

In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.

Image Retrieval regression +1

Active Learning for Open-set Annotation

no code implementations CVPR 2022 Kun-Peng Ning, Xun Zhao, Yu Li, Sheng-Jun Huang

To tackle this open-set annotation (OSA) problem, we propose a new active learning framework called LfOSA, which boosts the classification performance with an effective sampling strategy to precisely detect examples from known classes for annotation.

Active Learning

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

no code implementations NAACL 2022 Yu Li, Baolin Peng, Yelong Shen, Yi Mao, Lars Liden, Zhou Yu, Jianfeng Gao

To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks.

Dialogue Generation Language Modelling

Contrastive Cycle Adversarial Autoencoders for Single-cell Multi-omics Alignment and Integration

1 code implementation5 Dec 2021 Xuesong Wang, Zhihang Hu, Tingyang Yu, Ruijie Wang, Yumeng Wei, Juan Shu, Jianzhu Ma, Yu Li

Our approach can efficiently map the above data with high sparsity and noise from different spaces to a low-dimensional manifold in a unified space, making the downstream alignment and integration straightforward.

CLMB: deep contrastive learning for robust metagenomic binning

1 code implementation18 Nov 2021 Pengfei Zhang, Zhengyuan Jiang, YiXuan Wang, Yu Li

Essentially, instead of denoising the data explicitly, we add simulated noise to the training data and force the deep learning model to produce similar and stable representations for both the noise-free data and the distorted data.

Contrastive Learning Denoising

HMD-AMP: Protein Language-Powered Hierarchical Multi-label Deep Forest for Annotating Antimicrobial Peptides

no code implementations11 Nov 2021 Qinze Yu, Zhihang Dong, Xingyu Fan, Licheng Zong, Yu Li

Identifying the targets of an antimicrobial peptide is a fundamental step in studying the innate immune response and combating antibiotic resistance, and more broadly, precision medicine and public health.

Language Modelling Multi-Label Classification

Multi-Class Anomaly Detection

no code implementations28 Oct 2021 Suresh Singh, Minwei Luo, Yu Li

However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together.

Anomaly Detection

Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval

no code implementations ICLR 2022 Binjie Zhang, Yixiao Ge, Yantao Shen, Yu Li, Chun Yuan, Xuyuan Xu, Yexin Wang, Ying Shan

In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.

Image Retrieval regression +1

Orthogonal Graph Neural Networks

1 code implementation23 Sep 2021 Kai Guo, Kaixiong Zhou, Xia Hu, Yu Li, Yi Chang, Xin Wang

Graph neural networks (GNNs) have received tremendous attention due to their superiority in learning node representations.

Graph Classification

FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks

1 code implementation EMNLP 2021 Chen Liu, Mengchao Zhang, Zhibin Fu, Pan Hou, Yu Li

In natural language processing (NLP), state-of-the-art (SOTA) semi-supervised learning (SSL) frameworks have shown great performance on deep pre-trained language models such as BERT, and are expected to significantly reduce the demand for manual labeling.

Semi-Supervised Text Classification

Crash Report Data Analysis for Creating Scenario-Wise, Spatio-Temporal Attention Guidance to Support Computer Vision-based Perception of Fatal Crash Risks

no code implementations6 Sep 2021 Yu Li, Muhammad Monjurul Karim, Ruwen Qin

Then, exploratory analysis of location- and time-related variables of the crash report data suggests reducing fatal crashes to spatially defined groups.

Association

Spatial-Temporal Deep Intention Destination Networks for Online Travel Planning

no code implementations9 Aug 2021 Yu Li, Fei Xiong, Ziyi Wang, Zulong Chen, Chuanfei Xu, Yuyu Yin, Li Zhou

Therefore, in this paper, we focus on predicting users' intention destinations in online travel platforms.

Information Bottleneck Approach to Spatial Attention Learning

1 code implementation7 Aug 2021 Qiuxia Lai, Yu Li, Ailing Zeng, Minhao Liu, Hanqiu Sun, Qiang Xu

Extensive experiments show that the proposed IB-inspired spatial attention mechanism can yield attention maps that neatly highlight the regions of interest while suppressing backgrounds, and bootstrap standard DNN structures for visual recognition tasks (e. g., image classification, fine-grained recognition, cross-domain classification).

Decision Making Image Classification

LHRM: A LBS based Heterogeneous Relations Model for User Cold Start Recommendation in Online Travel Platform

no code implementations5 Aug 2021 Ziyi Wang, Wendong Xiao, Yu Li, Zulong Chen, Zhi Jiang

To alleviate this problem, existing user cold start methods either apply deep learning to build a cross-domain recommender system or map user attributes into the space of user behaviour.

Recommendation Systems

Towards explainable artificial intelligence (XAI) for early anticipation of traffic accidents

1 code implementation31 Jul 2021 Muhammad Monjurul Karim, Yu Li, Ruwen Qin

It confirms that the Grad-CAM chosen by this study can generate high-quality, human-interpretable saliency maps (with 1. 23 Normalized Scanpath Saliency) for explaining the crash anticipation decision.

Accident Anticipation Decision Making +1

Protein-RNA interaction prediction with deep learning: Structure matters

no code implementations26 Jul 2021 Junkang Wei, Siyuan Chen, Licheng Zong, Xin Gao, Yu Li

Protein-RNA interactions are of vital importance to a variety of cellular activities.

Tracking Instances as Queries

1 code implementation22 Jun 2021 Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Ying Shan, Bin Feng, Wenyu Liu

Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object detection, semantic segmentation, and instance segmentation.

Instance Segmentation object-detection +3

Learning Temporal Consistency for Low Light Video Enhancement From Single Images

1 code implementation CVPR 2021 Fan Zhang, Yu Li, ShaoDi You, Ying Fu

Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency.

Optical Flow Estimation Video Enhancement

The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity

no code implementations ACL 2021 David Gros, Yu Li, Zhou Yu

Humans are increasingly interacting with machines through language, sometimes in contexts where the user may not know they are talking to a machine (like over the phone or a text chatbot).

Chatbot

Towards Emotional Support Dialog Systems

1 code implementation ACL 2021 Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, Minlie Huang

Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats.

TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks

no code implementations NeurIPS 2021 Yu Li, Min Li, Qiuxia Lai, Yannan Liu, Qiang Xu

To be specific, we first build a similarity graph on test instances and training samples, and we conduct graph-based semi-supervised learning to extract contextual features.

Image Classification

AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference

no code implementations10 May 2021 Min Li, Yu Li, Ye Tian, Li Jiang, Qiang Xu

This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL) tasks more efficiently than state-of-the-art solutions.

Image Classification

Instances as Queries

5 code implementations ICCV 2021 Yuxin Fang, Shusheng Yang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage.

Instance Segmentation object-detection +2

LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing

1 code implementation ACL 2021 Yu Li, Josh Arnold, Feifan Yan, Weiyan Shi, Zhou Yu

We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk.

DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems

no code implementations16 Apr 2021 Yu Li, Shirley Anugrah Hayati, Weiyan Shi, Zhou Yu

It is important for sociable recommendation dialog systems to perform as both on-task content and social content to engage users and gain their favor.

dialog state tracking Movie Recommendation

Crossover Learning for Fast Online Video Instance Segmentation

1 code implementation ICCV 2021 Shusheng Yang, Yuxin Fang, Xinggang Wang, Yu Li, Chen Fang, Ying Shan, Bin Feng, Wenyu Liu

For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames.

Association Instance Segmentation +3

Beyond Categorical Label Representations for Image Classification

1 code implementation ICLR 2021 Boyuan Chen, Yu Li, Sunand Raghupathi, Hod Lipson

Our experiments reveal that high dimensional, high entropy labels achieve comparable accuracy to text (categorical) labels on the standard image classification task, but features learned through our label representations exhibit more robustness under various adversarial attacks and better effectiveness with a limited amount of training data.

Classification General Classification +1

CLiMP: A Benchmark for Chinese Language Model Evaluation

no code implementations EACL 2021 Beilei Xiang, Changbing Yang, Yu Li, Alex Warstadt, Katharina Kann

CLiMP consists of sets of 1, 000 minimal pairs (MPs) for 16 syntactic contrasts in Mandarin, covering 9 major Mandarin linguistic phenomena.

Language Modelling

Effects of spin orbit coupling in superconducting proximity devices -- application to $\mathrm{CoSi_2 / TiSi_2}$ heterostructures

no code implementations25 Jan 2021 Vivek Mishra, Yu Li, Fu-Chun Zhang andStefan Kirchner

Motivated by the recent findings of unconventional superconductivity in $\mathrm{CoSi_2 / TiSi_2}$ heterostructures, we study the effect of interface induced Rashba spin orbit coupling on the conductance of a three terminal ``T" shape superconducting device.

Superconductivity Mesoscale and Nanoscale Physics

Towards Real-World Blind Face Restoration with Generative Facial Prior

1 code implementation CVPR 2021 Xintao Wang, Yu Li, Honglun Zhang, Ying Shan

Blind face restoration usually relies on facial priors, such as facial geometry prior or reference prior, to restore realistic and faithful details.

Blind Face Restoration Video Super-Resolution

Refine and Imitate: Reducing Repetition and Inconsistency in Dialogue Generation via Reinforcement Learning and Human Demonstration

no code implementations1 Jan 2021 Weiyan Shi, Yu Li, Saurav Sahay, Zhou Yu

Despite the recent success of large-scale language models on various downstream NLP tasks, the repetition and inconsistency problems still persist in dialogue response generation.

Dialogue Generation Language Modelling +1

A Framework For Differentiable Discovery Of Graph Algorithms

no code implementations NeurIPS Workshop LMCA 2020 Hanjun Dai, Xinshi Chen, Yu Li, Xin Gao, Le Song

Recently there is a surge of interests in using graph neural networks (GNNs) to learn algorithms.

Exploring Balanced Feature Spaces for Representation Learning

no code implementations ICLR 2021 Bingyi Kang, Yu Li, Sa Xie, Zehuan Yuan, Jiashi Feng

Motivated by this question, we conduct a series of studies on the performance of self-supervised contrastive learning and supervised learning methods over multiple datasets where training instance distributions vary from a balanced one to a long-tailed one.

Contrastive Learning Long-tail Learning +2

AggMask: Exploring locally aggregated learning of mask representations for instance segmentation

1 code implementation1 Jan 2021 Tao Wang, Jun Hao Liew, Yu Li, Yunpeng Chen, Jiashi Feng

Recently proposed one-stage instance segmentation models (\emph{e. g.}, SOLO) learn to directly predict location-specific object mask with fully-convolutional networks.

Instance Segmentation Semantic Segmentation

Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

no code implementations Findings (EMNLP) 2021 Weiyan Shi, Yu Li, Saurav Sahay, Zhou Yu

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.

Language Modelling Response Generation

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

Interactive Key-Value Memory-augmented Attention for Image Paragraph Captioning

no code implementations COLING 2020 Chunpu Xu, Yu Li, Chengming Li, Xiang Ao, Min Yang, Jinwen Tian

In this paper, we propose an Interactive key-value Memory- augmented Attention model for image Paragraph captioning (IMAP) to keep track of the attention history (salient objects coverage information) along with the update-chain of the decoder state and therefore avoid generating repetitive or incomplete image descriptions.

Image Paragraph Captioning

A Simple Yet Effective Method for Video Temporal Grounding with Cross-Modality Attention

no code implementations23 Sep 2020 Binjie Zhang, Yu Li, Chun Yuan, Dejing Xu, Pin Jiang, Ying Shan

The task of language-guided video temporal grounding is to localize the particular video clip corresponding to a query sentence in an untrimmed video.

DeepDyve: Dynamic Verification for Deep Neural Networks

no code implementations21 Sep 2020 Yu Li, Min Li, Bo Luo, Ye Tian, Qiang Xu

The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much.

Autonomous Driving

Dual Semantic Fusion Network for Video Object Detection

no code implementations16 Sep 2020 Lijian Lin, Haosheng Chen, Honglun Zhang, Jun Liang, Yu Li, Ying Shan, Hanzi Wang

Video object detection is a tough task due to the deteriorated quality of video sequences captured under complex environments.

object-detection Optical Flow Estimation +1

Towards Structured Prediction in Bioinformatics with Deep Learning

no code implementations25 Aug 2020 Yu Li

However, in addition to the standard classification or regression problems, in bioinformatics, we often need to predict more complex structured targets, such as 2D images and 3D molecular structures.

Structured Prediction

The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation

1 code implementation ECCV 2020 Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Junhao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

Specifically, we systematically investigate performance drop of the state-of-the-art two-stage instance segmentation model Mask R-CNN on the recent long-tail LVIS dataset, and unveil that a major cause is the inaccurate classification of object proposals.

General Classification Instance Segmentation +3

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

2 code implementations CVPR 2020 Yu Li, Tao Wang, Bingyi Kang, Sheng Tang, Chunfeng Wang, Jintao Li, Jiashi Feng

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.

Image Classification Instance Segmentation +4

Learning to Stop While Learning to Predict

1 code implementation ICML 2020 Xinshi Chen, Hanjun Dai, Yu Li, Xin Gao, Le Song

Similar to algorithms, the optimal depth of a deep architecture may be different for different input instances, either to avoid ``over-thinking'', or because we want to compute less for operations converged already.

Meta-Learning

Learning to Dehaze from Realistic Scene with A Fast Physics-based Dehazing Network

no code implementations18 Apr 2020 Ruoteng Li, Xiaoyi Zhang, ShaoDi You, Yu Li

In this paper, we complement the existing datasets with a new, large, and diverse dehazing dataset containing real outdoor scenes from High-Definition (HD) 3D movies.

Autonomous Driving

RNA Secondary Structure Prediction By Learning Unrolled Algorithms

1 code implementation ICLR 2020 Xinshi Chen, Yu Li, Ramzan Umarov, Xin Gao, Le Song

The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled algorithm for constrained programming as the template for deep architectures to enforce constraints.

Fast Video Object Segmentation using the Global Context Module

no code implementations ECCV 2020 Yu Li, Zhuoran Shen, Ying Shan

Therefore, it uses constant memory regardless of the video length and costs substantially less memory and computation.

online learning Semantic Segmentation +3

Asymmetric GAN for Unpaired Image-to-image Translation

no code implementations25 Dec 2019 Yu Li, Sheng Tang, Rui Zhang, Yongdong Zhang, Jintao Li, Shuicheng Yan

While in situations where two domains are asymmetric in complexity, i. e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity.

Image-to-Image Translation Translation

Two Generator Game: Learning to Sample via Linear Goodness-of-Fit Test

no code implementations NeurIPS 2019 Lizhong Ding, Mengyang Yu, Li Liu, Fan Zhu, Yong liu, Yu Li, Ling Shao

DEAN can be interpreted as a GOF game between two generative networks, where one explicit generative network learns an energy-based distribution that fits the real data, and the other implicit generative network is trained by minimizing a GOF test statistic between the energy-based distribution and the generated data, such that the underlying distribution of the generated data is close to the energy-based distribution.

End-to-End Trainable Non-Collaborative Dialog System

1 code implementation25 Nov 2019 Yu Li, Kun Qian, Weiyan Shi, Zhou Yu

End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task.

On Functional Test Generation for Deep Neural Network IPs

no code implementations23 Nov 2019 Bo Luo, Yu Li, Lingxiao Wei, Qiang Xu

Considering the large amount of training data and know-how required to generate the network, it is more practical to use third-party DNN intellectual property (IP) cores for many designs.

Unsupervised Learning for Intrinsic Image Decomposition from a Single Image

2 code implementations CVPR 2020 Yunfei Liu, Yu Li, ShaoDi You, Feng Lu

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene.

Intrinsic Image Decomposition

Classification Calibration for Long-tail Instance Segmentation

1 code implementation29 Oct 2019 Tao Wang, Yu Li, Bingyi Kang, Junnan Li, Jun Hao Liew, Sheng Tang, Steven Hoi, Jiashi Feng

In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals.

Classification General Classification +2

Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models

1 code implementation EACL 2021 Qingyang Wu, Yichi Zhang, Yu Li, Zhou Yu

Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks.

Language Modelling Response Generation

Multi-sensor cloud and cloud shadow segmentation with a convolutional neural network

1 code implementation Remote Sensing of Environment 2019 Marc Wieland, Yu Li, Sandro Martinis

The rule-based Fmask method takes significantly longer (277. 8 s/megapixel) and produces results with an accuracy of 0. 75, Kappa of 0. 60 and Dice coefficient of 0. 72.

Semantic Segmentation

Attention Guided Low-light Image Enhancement with a Large Scale Low-light Simulation Dataset

3 code implementations2 Aug 2019 Feifan Lv, Yu Li, Feng Lu

Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark.

 Ranked #1 on Low-Light Image Enhancement on 3DMatch Benchmark (using extra training data)

Denoising Low-Light Image Enhancement

Semantic Guided Single Image Reflection Removal

1 code implementation27 Jul 2019 Yunfei Liu, Yu Li, ShaoDi You, Feng Lu

Reflection is common in images capturing scenes behind a glass window, which is not only a disturbance visually but also influence the performance of other computer vision algorithms.

Reflection Removal

Hyperspectral City V1.0 Dataset and Benchmark

no code implementations24 Jul 2019 Shaodi You, Erqi Huang, Shuaizhe Liang, Yongrong Zheng, Yunxiang Li, Fan Wang, Sen Lin, Qiu Shen, Xun Cao, Diming Zhang, Yuanjiang Li, Yu Li, Ying Fu, Boxin Shi, Feng Lu, Yinqiang Zheng, Robby T. Tan

This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.

Computer-aided Detection of Squamous Carcinoma of the Cervix in Whole Slide Images

no code implementations27 May 2019 Ye Tian, Li Yang, Wei Wang, Jing Zhang, Qing Tang, Mili Ji, Yang Yu, Yu Li, Hong Yang, Airong Qian

Traditionally, the most indispensable diagnosis of cervix squamous carcinoma is histopathological assessment which is achieved under microscope by pathologist.

whole slide images

Image-based reconstruction for the impact problems by using DPNNs

no code implementations8 Apr 2019 Yu Li, Hu Wang, Wenquan Shuai, Honghao Zhang, Yong Peng

Therefore, in this study, an improved ReConNN method is proposed to address the mentioned weaknesses.

Deep learning in bioinformatics: introduction, application, and perspective in big data era

1 code implementation28 Feb 2019 Yu Li, Chao Huang, Lizhong Ding, Zhongxiao Li, Yijie Pan, Xin Gao

Deep learning, which is especially formidable in handling big data, has achieved great success in various fields, including bioinformatics.

On Configurable Defense against Adversarial Example Attacks

no code implementations6 Dec 2018 Bo Luo, Min Li, Yu Li, Qiang Xu

Machine learning systems based on deep neural networks (DNNs) have gained mainstream adoption in many applications.

Sample-Efficient Policy Learning based on Completely Behavior Cloning

no code implementations9 Nov 2018 Qiming Zou, Ling Wang, Ke Lu, Yu Li

Direct policy search is one of the most important algorithm of reinforcement learning.

Style Separation and Synthesis via Generative Adversarial Networks

2 code implementations7 Nov 2018 Rui Zhang, Sheng Tang, Yu Li, Junbo Guo, Yongdong Zhang, Jintao Li, Shuicheng Yan

The S3-GAN consists of an encoder network, a generator network, and an adversarial network.

Image-Based Reconstruction for a 3D-PFHS Heat Transfer Problem by ReConNN

no code implementations6 Nov 2018 Yu Li, Hu Wang, Xinjian Deng

Therefore, an image-based reconstruction model of a heat transfer process for a 3D-PFHS is established.

Fast and accurate algorithms for the computation of spherically symmetric nonlocal diffusion operators on lattices

4 code implementations16 Oct 2018 Yu Li, Richard Mikael Slevinsky

We present a unified treatment of the Fourier spectra of spherically symmetric nonlocal diffusion operators.

Numerical Analysis 33C20, 41A20

PromID: human promoter prediction by deep learning

no code implementations2 Oct 2018 Ramzan Umarov, Hiroyuki Kuwahara, Yu Li, Xin Gao, Victor Solovyev

In this work we further develop our deep learning approach that was relatively successful to discriminate short promoter and non-promoter sequences.

Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks

no code implementations3 Sep 2018 Zhixiang Hao, Yu Li, ShaoDi You, Feng Lu

However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application.

Depth Estimation

On the Decision Boundary of Deep Neural Networks

1 code implementation16 Aug 2018 Yu Li, Lizhong Ding, Xin Gao

We demonstrate, both theoretically and empirically, that the last weight layer of a neural network converges to a linear SVM trained on the output of the last hidden layer, for both the binary case and the multi-class case with the commonly used cross-entropy loss.

Clause Vivification by Unit Propagation in CDCL SAT Solvers

no code implementations29 Jul 2018 Chu-min Li, Fan Xiao, Mao Luo, Felip Manyà, Zhipeng Lü, Yu Li

Original and learnt clauses in Conflict-Driven Clause Learning (CDCL) SAT solvers often contain redundant literals.

SupportNet: solving catastrophic forgetting in class incremental learning with support data

1 code implementation8 Jun 2018 Yu Li, Zhongxiao Li, Lizhong Ding, Yijie Pan, Chao Huang, Yuhui Hu, Wei Chen, Xin Gao

A plain well-trained deep learning model often does not have the ability to learn new knowledge without forgetting the previously learned knowledge, which is known as catastrophic forgetting.

class-incremental learning Incremental Learning

Webpage Saliency Prediction with Two-stage Generative Adversarial Networks

no code implementations29 May 2018 Yu Li, Ya zhang

Web page saliency prediction is a challenge problem in image transformation and computer vision.

Saliency Prediction

DLBI: Deep learning guided Bayesian inference for structure reconstruction of super-resolution fluorescence microscopy

1 code implementation20 May 2018 Yu Li, Fan Xu, Fa Zhang, Pingyong Xu, Mingshu Zhang, Ming Fan, Lihua Li, Xin Gao, Renmin Han

Our method combines the strength of deep learning and statistical inference, where deep learning captures the underlying distribution of the fluorophores that are consistent with the observed time-series fluorescent images by exploring local features and correlation along time-axis, and statistical inference further refines the ultrastructure extracted by deep learning and endues physical meaning to the final image.

Bayesian Inference Super-Resolution +2

Reconstruction of Simulation-Based Physical Field by Reconstruction Neural Network Method

no code implementations19 Apr 2018 Yu Li, Hu Wang, Kangjia Mo, Tao Zeng

In such a framework, a reconstruction neural network (ReConNN) model designed for simulation-based physical field's reconstruction is proposed.

I Know What You See: Power Side-Channel Attack on Convolutional Neural Network Accelerators

no code implementations5 Mar 2018 Lingxiao Wei, Bo Luo, Yu Li, Yannan Liu, Qiang Xu

Deep learning has become the de-facto computational paradigm for various kinds of perception problems, including many privacy-sensitive applications such as online medical image analysis.

Can CNN Construct Highly Accurate Models Efficiently for High-Dimensional Problems in Complex Product Designs?

no code implementations15 Nov 2017 Yu Li, Hu Wang, Juanjuan Liu

In order to evaluate the proposed CNN metamodel for hundreds-dimensional and strong nonlinear problems, CNN is compared with other metamodeling techniques.

LIME: Low-light Image Enhancement via Illumination Map Estimation

2 code implementations IEEE TIP 2016 Xiaojie Guo, Yu Li, Haibin Ling

When one captures images in low-light conditions, the images often suffer from low visibility.

 Ranked #1 on Low-Light Image Enhancement on 10 Monkey Species (using extra training data)

Low-Light Image Enhancement

Haze Visibility Enhancement: A Survey and Quantitative Benchmarking

no code implementations21 Jul 2016 Yu Li, ShaoDi You, Michael S. Brown, Robby T. Tan

This paper provides a comprehensive survey of methods dealing with visibility enhancement of images taken in hazy or foggy scenes.

Nighttime Haze Removal With Glow and Multiple Light Colors

no code implementations ICCV 2015 Yu Li, Robby T. Tan, Michael S. Brown

We demonstrate the effectiveness of our nighttime haze model and correction method on a number of examples and compare our results with existing daytime and nighttime dehazing methods' results.

SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs

no code implementations ICCV 2015 Yu Li, Dongbo Min, Michael S. Brown, Minh N. Do, Jiangbo Lu

However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.

Optical Flow Estimation

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