Search Results for author: LiWei Wang

Found 105 papers, 50 papers with code

RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging

no code implementations EMNLP 2021 Jie Hao, Linfeng Song, LiWei Wang, Kun Xu, Zhaopeng Tu, Dong Yu

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.

Dialogue Rewriting Text Generation

VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control

1 code implementation18 Aug 2023 Zi-Yuan Hu, Yanyang Li, Michael R. Lyu, LiWei Wang

In particular, our VL-PET-large with lightweight PET module designs significantly outperforms VL-Adapter by 2. 92% (3. 41%) and LoRA by 3. 37% (7. 03%) with BART-base (T5-base) on image-text tasks.

Image Captioning Text Generation +4

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

2 code implementations15 Aug 2023 Haiyang Wang, Hao Tang, Shaoshuai Shi, Aoxue Li, Zhenguo Li, Bernt Schiele, LiWei Wang

Jointly processing information from multiple sensors is crucial to achieving accurate and robust perception for reliable autonomous driving systems.

3D Object Detection Autonomous Driving +2

GRU-D-Weibull: A Novel Real-Time Individualized Endpoint Prediction

no code implementations14 Aug 2023 Xiaoyang Ruan, LiWei Wang, Charat Thongprayoon, Wisit Cheungpasitporn, Hongfang Liu

Our findings demonstrate the considerable potential of GRU-D-Weibull as the next-generation architecture for endpoint risk management, capable of generating various endpoint estimates for real-time monitoring using clinical data.


CLEVA: Chinese Language Models EVAluation Platform

no code implementations9 Aug 2023 Yanyang Li, Jianqiao Zhao, Duo Zheng, Zi-Yuan Hu, Zhi Chen, Xiaohui Su, Yongfeng Huang, Shijia Huang, Dahua Lin, Michael R. Lyu, LiWei Wang

With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model's capabilities has become an increasingly significant issue.

Topology-Preserving Automatic Labeling of Coronary Arteries via Anatomy-aware Connection Classifier

1 code implementation22 Jul 2023 Zhixing Zhang, Ziwei Zhao, Dong Wang, Shishuang Zhao, Yuhang Liu, Jia Liu, LiWei Wang

Automatic labeling of coronary arteries is an essential task in the practical diagnosis process of cardiovascular diseases.


Data-Driven Design for Metamaterials and Multiscale Systems: A Review

no code implementations1 Jul 2023 Doksoo Lee, Wei Wayne Chen, LiWei Wang, Yu-Chin Chan, Wei Chen

Metamaterials are artificial materials designed to exhibit effective material parameters that go beyond those found in nature.

Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers

no code implementations12 Jun 2023 AnLan Sun, Zhao Zhang, Meng Lei, Yuting Dai, Dong Wang, LiWei Wang

The coherence loss uses the feature centers generated by the static images to guide the frame attention in the video model.

Video Classification

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds

no code implementations12 Jun 2023 Jiayi Huang, Han Zhong, LiWei Wang, Lin F. Yang

Our algorithm, termed as \textsc{Heavy-LSVI-UCB}, achieves the \emph{first} computationally efficient \emph{instance-dependent} $K$-episode regret of $\tilde{O}(d \sqrt{H \mathcal{U}^*} K^\frac{1}{1+\epsilon} + d \sqrt{H \mathcal{V}^* K})$.

Open-Ended Question Answering Reinforcement Learning (RL)

Mining Negative Temporal Contexts For False Positive Suppression In Real-Time Ultrasound Lesion Detection

1 code implementation29 May 2023 Haojun Yu, Youcheng Li, Quanlin Wu, Ziwei Zhao, Dengbo Chen, Dong Wang, LiWei Wang

To address this issue, we propose to extract contexts from previous frames, including NTC, with the guidance of inverse optical flow.

Lesion Detection object-detection +2

Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective

1 code implementation24 May 2023 Guhao Feng, Bohang Zhang, Yuntian Gu, Haotian Ye, Di He, LiWei Wang

We start by giving an impossibility result showing that bounded-depth Transformers are unable to directly produce correct answers for basic arithmetic/equation tasks unless the model size grows super-polynomially with respect to the input length.

Decision Making

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning

no code implementations CVPR 2023 Hao Yang, Lanqing Hong, Aoxue Li, Tianyang Hu, Zhenguo Li, Gim Hee Lee, LiWei Wang

In this work, we first investigate the effects of synthetic data in synthetic-to-real novel view synthesis and surprisingly observe that models trained with synthetic data tend to produce sharper but less accurate volume densities.

Contrastive Learning Generalizable Novel View Synthesis +2

A Cross-institutional Evaluation on Breast Cancer Phenotyping NLP Algorithms on Electronic Health Records

no code implementations15 Mar 2023 Sicheng Zhou, Nan Wang, LiWei Wang, Ju Sun, Anne Blaes, Hongfang Liu, Rui Zhang

We developed three types of NLP models (i. e., conditional random field, bi-directional long short-term memory and CancerBERT) to extract cancer phenotypes from clinical texts.

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

no code implementations3 Feb 2023 Yunchang Yang, Han Zhong, Tianhao Wu, Bin Liu, LiWei Wang, Simon S. Du

We study stochastic delayed feedback in general multi-agent sequential decision making, which includes bandits, single-agent Markov decision processes (MDPs), and Markov games (MGs).

Decision Making

Rethinking the Expressive Power of GNNs via Graph Biconnectivity

1 code implementation23 Jan 2023 Bohang Zhang, Shengjie Luo, LiWei Wang, Di He

In this paper, we take a fundamentally different perspective to study the expressive power of GNNs beyond the WL test.

GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond

no code implementations3 Nov 2022 Han Zhong, Wei Xiong, Sirui Zheng, LiWei Wang, Zhaoran Wang, Zhuoran Yang, Tong Zhang

The proposed algorithm modifies the standard posterior sampling algorithm in two aspects: (i) we use an optimistic prior distribution that biases towards hypotheses with higher values and (ii) a loglikelihood function is set to be the empirical loss evaluated on the historical data, where the choice of loss function supports both model-free and model-based learning.

Decision Making Reinforcement Learning (RL)

A 5G Enabled Adaptive Computing Workflow for Greener Power Grid

no code implementations31 Oct 2022 Yousu Chen, LiWei Wang, Xiaoyuan Fan, Dexin Wang, James Ogle

5G wireless technology can deliver higher data speeds, ultra low latency, more reliability, massive network capacity, increased availability, and a more uniform user experience to users.

Cloud Computing Edge-computing

Provable Sim-to-real Transfer in Continuous Domain with Partial Observations

no code implementations27 Oct 2022 Jiachen Hu, Han Zhong, Chi Jin, LiWei Wang

Sim-to-real transfer trains RL agents in the simulated environments and then deploys them in the real world.

On the Power of Pre-training for Generalization in RL: Provable Benefits and Hardness

no code implementations19 Oct 2022 Haotian Ye, Xiaoyu Chen, LiWei Wang, Simon S. Du

Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment.

Reinforcement Learning (RL)

Denoising Masked AutoEncoders Help Robust Classification

1 code implementation10 Oct 2022 Quanlin Wu, Hang Ye, Yuntian Gu, Huishuai Zhang, LiWei Wang, Di He

In this paper, we propose a new self-supervised method, which is called Denoising Masked AutoEncoders (DMAE), for learning certified robust classifiers of images.

Classification Denoising +1

One Transformer Can Understand Both 2D & 3D Molecular Data

1 code implementation4 Oct 2022 Shengjie Luo, Tianlang Chen, Yixian Xu, Shuxin Zheng, Tie-Yan Liu, LiWei Wang, Di He

To achieve this goal, in this work, we develop a novel Transformer-based Molecular model called Transformer-M, which can take molecular data of 2D or 3D formats as input and generate meaningful semantic representations.

Graph Regression molecular representation +1

Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective

1 code implementation4 Oct 2022 Bohang Zhang, Du Jiang, Di He, LiWei Wang

Designing neural networks with bounded Lipschitz constant is a promising way to obtain certifiably robust classifiers against adversarial examples.

Robust classification

PointScatter: Point Set Representation for Tubular Structure Extraction

1 code implementation13 Sep 2022 Dong Wang, Zhao Zhang, Ziwei Zhao, Yuhang Liu, Yihong Chen, LiWei Wang

Inspired by this, we propose PointScatter, an alternative to the segmentation models for the tubular structure extraction task.

Check and Link: Pairwise Lesion Correspondence Guides Mammogram Mass Detection

no code implementations13 Sep 2022 Ziwei Zhao, Dong Wang, Yihong Chen, Ziteng Wang, LiWei Wang

In mammogram mass detection, modeling pairwise lesion correspondence explicitly is particularly important.

Lesion Detection

Boosting 3D Object Detection via Object-Focused Image Fusion

1 code implementation21 Jul 2022 Hao Yang, Chen Shi, Yihong Chen, LiWei Wang

Given a set of point features and image feature maps, DeMF adaptively aggregates image features by taking the projected 2D location of the 3D point as reference.

3D Object Detection object-detection

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

1 code implementation20 Jul 2022 Xin Lai, Zhuotao Tian, Xiaogang Xu, Yingcong Chen, Shu Liu, Hengshuang Zhao, LiWei Wang, Jiaya Jia

Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations.

Semantic Segmentation Unsupervised Domain Adaptation

Is $L^2$ Physics-Informed Loss Always Suitable for Training Physics-Informed Neural Network?

1 code implementation4 Jun 2022 Chuwei Wang, Shanda Li, Di He, LiWei Wang

In particular, we leverage the concept of stability in the literature of partial differential equation to study the asymptotic behavior of the learned solution as the loss approaches zero.

Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game

no code implementations31 May 2022 Wei Xiong, Han Zhong, Chengshuai Shi, Cong Shen, LiWei Wang, Tong Zhang

We also extend our techniques to the two-player zero-sum Markov games (MGs), and establish a new performance lower bound for MGs, which tightens the existing result, and verifies the nearly minimax optimality of the proposed algorithm.

Offline RL Reinforcement Learning (RL)

Voxel Field Fusion for 3D Object Detection

1 code implementation CVPR 2022 Yanwei Li, Xiaojuan Qi, Yukang Chen, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion.

3D Object Detection Data Augmentation +1

Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power

no code implementations27 May 2022 Binghui Li, Jikai Jin, Han Zhong, John E. Hopcroft, LiWei Wang

Moreover, we establish an improved upper bound of $\exp({\mathcal{O}}(k))$ for the network size to achieve low robust generalization error when the data lies on a manifold with intrinsic dimension $k$ ($k \ll d$).

Binary Classification

Your Transformer May Not be as Powerful as You Expect

1 code implementation26 May 2022 Shengjie Luo, Shanda Li, Shuxin Zheng, Tie-Yan Liu, LiWei Wang, Di He

Extensive experiments covering typical architectures and tasks demonstrate that our model is parameter-efficient and can achieve superior performance to strong baselines in a wide range of applications.

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency

no code implementations ACL 2022 Yanyang Li, Fuli Luo, Runxin Xu, Songfang Huang, Fei Huang, LiWei Wang

Structured pruning has been extensively studied on monolingual pre-trained language models and is yet to be fully evaluated on their multilingual counterparts.

RBGNet: Ray-based Grouping for 3D Object Detection

1 code implementation CVPR 2022 Haiyang Wang, Shaoshuai Shi, Ze Yang, Rongyao Fang, Qi Qian, Hongsheng Li, Bernt Schiele, LiWei Wang

In order to learn better representations of object shape to enhance cluster features for predicting 3D boxes, we propose a ray-based feature grouping module, which aggregates the point-wise features on object surfaces using a group of determined rays uniformly emitted from cluster centers.

3D Object Detection object-detection

Multi-View Transformer for 3D Visual Grounding

1 code implementation CVPR 2022 Shijia Huang, Yilun Chen, Jiaya Jia, LiWei Wang

The multi-view space enables the network to learn a more robust multi-modal representation for 3D visual grounding and eliminates the dependence on specific views.

Visual Grounding

Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors

1 code implementation4 Apr 2022 Wanyu Du, Jianqiao Zhao, LiWei Wang, Yangfeng Ji

The proposed stochastic function is sampled from a Gaussian process prior to (1) provide infinite number of joint Gaussian distributions of random context variables (diversity-promoting) and (2) explicitly model dependency between context variables (accurate-encoding).

Gaussian Processes Paraphrase Generation +4

Stratified Transformer for 3D Point Cloud Segmentation

4 code implementations CVPR 2022 Xin Lai, Jianhui Liu, Li Jiang, LiWei Wang, Hengshuang Zhao, Shu Liu, Xiaojuan Qi, Jiaya Jia

In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance.

Point Cloud Segmentation Semantic Segmentation

Reconstruction Task Finds Universal Winning Tickets

no code implementations23 Feb 2022 Ruichen Li, Binghui Li, Qi Qian, LiWei Wang

Pruning well-trained neural networks is effective to achieve a promising accuracy-efficiency trade-off in computer vision regimes.

Image Reconstruction object-detection +1

t-METASET: Tailoring Property Bias of Large-Scale Metamaterial Datasets through Active Learning

no code implementations21 Feb 2022 Doksoo Lee, Yu-Chin Chan, Wei Wayne Chen, LiWei Wang, Anton van Beek, Wei Chen

Distinctly, we seek a solution to a commonplace yet frequently overlooked scenario at early stages of data-driven design of metamaterials: when a massive (~O(10^4 )) shape-only library has been prepared with no properties evaluated.

Active Learning

Learning Physics-Informed Neural Networks without Stacked Back-propagation

1 code implementation18 Feb 2022 Di He, Shanda Li, Wenlei Shi, Xiaotian Gao, Jia Zhang, Jiang Bian, LiWei Wang, Tie-Yan Liu

In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks.

Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets

no code implementations15 Feb 2022 Han Zhong, Wei Xiong, Jiyuan Tan, LiWei Wang, Tong Zhang, Zhaoran Wang, Zhuoran Yang

When the dataset does not have uniform coverage over all policy pairs, finding an approximate NE involves challenges in three aspects: (i) distributional shift between the behavior policy and the optimal policy, (ii) function approximation to handle large state space, and (iii) minimax optimization for equilibrium solving.

FlowEval: A Consensus-Based Dialogue Evaluation Framework Using Segment Act Flows

no code implementations14 Feb 2022 Jianqiao Zhao, Yanyang Li, Wanyu Du, Yangfeng Ji, Dong Yu, Michael R. Lyu, LiWei Wang

Hence, we propose segment act, an extension of dialog act from utterance level to segment level, and crowdsource a large-scale dataset for it.

Dialogue Evaluation

Nearly Optimal Policy Optimization with Stable at Any Time Guarantee

no code implementations21 Dec 2021 Tianhao Wu, Yunchang Yang, Han Zhong, LiWei Wang, Simon S. Du, Jiantao Jiao

Policy optimization methods are one of the most widely used classes of Reinforcement Learning (RL) algorithms.

Reinforcement Learning (RL)

Remixing Functionally Graded Structures: Data-Driven Topology Optimization with Multiclass Shape Blending

1 code implementation1 Dec 2021 Yu-Chin Chan, Daicong Da, LiWei Wang, Wei Chen

We propose to inherit the advantages of both through a data-driven framework for multiclass functionally graded structures that mixes several families, i. e., classes, of microstructure topologies to create spatially-varying designs with guaranteed feasibility.

Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs

no code implementations NeurIPS 2021 Han Zhong, Jiayi Huang, Lin F. Yang, LiWei Wang

Despite a large amount of effort in dealing with heavy-tailed error in machine learning, little is known when moments of the error can become non-existential: the random noise $\eta$ satisfies Pr$\left[|\eta| > |y|\right] \le 1/|y|^{\alpha}$ for some $\alpha > 0$.

Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis

no code implementations NeurIPS 2021 Jikai Jin, Bohang Zhang, Haiyang Wang, LiWei Wang

Distributionally robust optimization (DRO) is a widely-used approach to learn models that are robust against distribution shift.

Boosting the Certified Robustness of L-infinity Distance Nets

2 code implementations ICLR 2022 Bohang Zhang, Du Jiang, Di He, LiWei Wang

Recently, Zhang et al. (2021) developed a new neural network architecture based on $\ell_\infty$-distance functions, which naturally possesses certified $\ell_\infty$ robustness by its construction.

Semi-Supervised Semantic Segmentation via Adaptive Equalization Learning

1 code implementation NeurIPS 2021 Hanzhe Hu, Fangyun Wei, Han Hu, Qiwei Ye, Jinshi Cui, LiWei Wang

The confidence bank is leveraged as an indicator to tilt training towards under-performing categories, instantiated in three strategies: 1) adaptive Copy-Paste and CutMix data augmentation approaches which give more chance for under-performing categories to be copied or cut; 2) an adaptive data sampling approach to encourage pixels from under-performing category to be sampled; 3) a simple yet effective re-weighting method to alleviate the training noise raised by pseudo-labeling.

Data Augmentation Semi-Supervised Semantic Segmentation

Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver

no code implementations ICLR 2022 Xiaoyu Chen, Jiachen Hu, Lin F. Yang, LiWei Wang

In particular, we take a plug-in solver approach, where we focus on learning a model in the exploration phase and demand that \emph{any planning algorithm} on the learned model can give a near-optimal policy.

Model-based Reinforcement Learning Reinforcement Learning (RL)

Deep Structured Instance Graph for Distilling Object Detectors

1 code implementation ICCV 2021 Yixin Chen, Pengguang Chen, Shu Liu, LiWei Wang, Jiaya Jia

Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks.

Instance Segmentation Knowledge Distillation +3

CancerBERT: a BERT model for Extracting Breast Cancer Phenotypes from Electronic Health Records

no code implementations25 Aug 2021 Sicheng Zhou, LiWei Wang, Nan Wang, Hongfang Liu, Rui Zhang

This data used in the study included 21, 291 breast cancer patients diagnosed from 2010 to 2020, patients' clinical notes and pathology reports were collected from the University of Minnesota Clinical Data Repository (UMN).


Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision

1 code implementation17 Aug 2021 Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, Yukang Chen, Lu Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.

Panoptic Segmentation Weakly-supervised panoptic segmentation

A fast asynchronous MCMC sampler for sparse Bayesian inference

1 code implementation14 Aug 2021 Yves Atchadé, LiWei Wang

We propose a very fast approximate Markov Chain Monte Carlo (MCMC) sampling framework that is applicable to a large class of sparse Bayesian inference problems, where the computational cost per iteration in several models is of order $O(ns)$, where $n$ is the sample size, and $s$ the underlying sparsity of the model.

Bayesian Inference

Conditional Temporal Variational AutoEncoder for Action Video Prediction

no code implementations12 Aug 2021 Xiaogang Xu, Yi Wang, LiWei Wang, Bei Yu, Jiaya Jia

To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.

motion prediction Video Prediction

Collaborative Visual Navigation

1 code implementation2 Jul 2021 Haiyang Wang, Wenguan Wang, Xizhou Zhu, Jifeng Dai, LiWei Wang

As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques.

Multi-agent Reinforcement Learning Navigate +1

Scalable Gaussian Processes for Data-Driven Design using Big Data with Categorical Factors

no code implementations26 Jun 2021 LiWei Wang, Suraj Yerramilli, Akshay Iyer, Daniel Apley, Ping Zhu, Wei Chen

In addition, an interpretable latent space is obtained to draw insights into the effect of categorical factors, such as those associated with building blocks of architectures and element choices in metamaterial and materials design.

Gaussian Processes Variational Inference

Multi-stage Optimization based Adversarial Training

no code implementations26 Jun 2021 Xiaosen Wang, Chuanbiao Song, LiWei Wang, Kun He

In this work, we aim to avoid the catastrophic overfitting by introducing multi-step adversarial examples during the single-step adversarial training.

Adversarial Robustness

Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding

no code implementations NeurIPS 2021 Shengjie Luo, Shanda Li, Tianle Cai, Di He, Dinglan Peng, Shuxin Zheng, Guolin Ke, LiWei Wang, Tie-Yan Liu

Since in many state-of-the-art models, relative positional encoding is used as default, designing efficient Transformers that can incorporate RPE is appealing.

FedCM: Federated Learning with Client-level Momentum

1 code implementation21 Jun 2021 Jing Xu, Sen Wang, LiWei Wang, Andrew Chi-Chih Yao

Federated Learning is a distributed machine learning approach which enables model training without data sharing.

Federated Learning

Self-Supervised 3D Mesh Reconstruction From Single Images

no code implementations CVPR 2021 Tao Hu, LiWei Wang, Xiaogang Xu, Shu Liu, Jiaya Jia

Recent single-view 3D reconstruction methods reconstruct object's shape and texture from a single image with only 2D image-level annotation.

3D Reconstruction Image Generation +1

JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs

1 code implementation Findings (ACL) 2021 Pei Ke, Haozhe Ji, Yu Ran, Xin Cui, LiWei Wang, Linfeng Song, Xiaoyan Zhu, Minlie Huang

Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.

Graph Reconstruction KG-to-Text Generation +3

Data-Driven Multiscale Design of Cellular Composites with Multiclass Microstructures for Natural Frequency Maximization

no code implementations11 Jun 2021 LiWei Wang, Anton van Beek, Daicong Da, Yu-Chin Chan, Ping Zhu, Wei Chen

After integrating LVGP with the density-based TO, an efficient data-driven cellular composite optimization process is developed to enable concurrent exploration of microstructure concepts and the associated volume fractions for natural frequency optimization.

Towards a Theoretical Framework of Out-of-Distribution Generalization

no code implementations NeurIPS 2021 Haotian Ye, Chuanlong Xie, Tianle Cai, Ruichen Li, Zhenguo Li, LiWei Wang

We also introduce a new concept of expansion function, which characterizes to what extent the variance is amplified in the test domains over the training domains, and therefore give a quantitative meaning of invariant features.

Domain Generalization Model Selection +1

SAT: 2D Semantics Assisted Training for 3D Visual Grounding

1 code implementation ICCV 2021 Zhengyuan Yang, Songyang Zhang, LiWei Wang, Jiebo Luo

3D visual grounding aims at grounding a natural language description about a 3D scene, usually represented in the form of 3D point clouds, to the targeted object region.

Representation Learning Visual Grounding

Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection

1 code implementation CVPR 2021 Hanzhe Hu, Shuai Bai, Aoxue Li, Jinshi Cui, LiWei Wang

In this work, aiming to fully exploit features of annotated novel object and capture fine-grained features of query object, we propose Dense Relation Distillation with Context-aware Aggregation (DCNet) to tackle the few-shot detection problem.

Few-Shot Object Detection Meta-Learning +1

DAGN: Discourse-Aware Graph Network for Logical Reasoning

2 code implementations NAACL 2021 Yinya Huang, Meng Fang, Yu Cao, LiWei Wang, Xiaodan Liang

The model encodes discourse information as a graph with elementary discourse units (EDUs) and discourse relations, and learns the discourse-aware features via a graph network for downstream QA tasks.

Logical Reasoning

Revisiting Language Encoding in Learning Multilingual Representations

1 code implementation16 Feb 2021 Shengjie Luo, Kaiyuan Gao, Shuxin Zheng, Guolin Ke, Di He, LiWei Wang, Tie-Yan Liu

The language embedding can be either added to the word embedding or attached at the beginning of the sentence.

Word Embeddings

Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons

2 code implementations10 Feb 2021 Bohang Zhang, Tianle Cai, Zhou Lu, Di He, LiWei Wang

This directly provides a rigorous guarantee of the certified robustness based on the margin of prediction outputs.

Near-optimal Representation Learning for Linear Bandits and Linear RL

no code implementations8 Feb 2021 Jiachen Hu, Xiaoyu Chen, Chi Jin, Lihong Li, LiWei Wang

This paper studies representation learning for multi-task linear bandits and multi-task episodic RL with linear value function approximation.

Representation Learning

Learning Contextual Perturbation Budgets for Training Robust Neural Networks

no code implementations1 Jan 2021 Jing Xu, Zhouxing Shi, huan zhang, JinFeng Yi, Cho-Jui Hsieh, LiWei Wang

We also demonstrate that the perturbation budget generator can produce semantically-meaningful budgets, which implies that the generator can capture contextual information and the sensitivity of different features in a given image.

AT-GAN: An Adversarial Generative Model for Non-constrained Adversarial Examples

no code implementations1 Jan 2021 Xiaosen Wang, Kun He, Chuanbiao Song, LiWei Wang, John E. Hopcroft

A recent work targets unrestricted adversarial example using generative model but their method is based on a search in the neighborhood of input noise, so actually their output is still constrained by input.

Adversarial Attack Transfer Learning

Region-Aware Contrastive Learning for Semantic Segmentation

1 code implementation ICCV 2021 Hanzhe Hu, Jinshi Cui, LiWei Wang

Inspired by recent progress in unsupervised contrastive learning, we propose the region-aware contrastive learning (RegionContrast) for semantic segmentation in the supervised manner.

Contrastive Learning Semantic Segmentation

Pretrain-to-Finetune Adversarial Training via Sample-wise Randomized Smoothing

no code implementations1 Jan 2021 Lei Wang, Runtian Zhai, Di He, LiWei Wang, Li Jian

For certification, we carefully allocate specific robust regions for each test sample.

Robust Dialogue Utterance Rewriting as Sequence Tagging

1 code implementation29 Dec 2020 Jie Hao, Linfeng Song, LiWei Wang, Kun Xu, Zhaopeng Tu, Dong Yu

The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context.

Dialogue Rewriting Text Generation

Fully Convolutional Networks for Panoptic Segmentation

6 code implementations CVPR 2021 Yanwei Li, Hengshuang Zhao, Xiaojuan Qi, LiWei Wang, Zeming Li, Jian Sun, Jiaya Jia

In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN.

 Ranked #1 on Panoptic Segmentation on Mapillary val (PQth metric)

Panoptic Segmentation

Learnable Boundary Guided Adversarial Training

3 code implementations ICCV 2021 Jiequan Cui, Shu Liu, LiWei Wang, Jiaya Jia

Previous adversarial training raises model robustness under the compromise of accuracy on natural data.

Adversarial Defense

Semi-Supervised Learning for Video Captioning

no code implementations Findings of the Association for Computational Linguistics 2020 Ke Lin, Zhuoxin Gan, LiWei Wang

In the proposed study, we make the first attempt to train the video captioning model on labeled data and unlabeled data jointly, in a semi-supervised learning manner.

Video Captioning

Improved Analysis of Clipping Algorithms for Non-convex Optimization

1 code implementation NeurIPS 2020 Bohang Zhang, Jikai Jin, Cong Fang, LiWei Wang

Gradient clipping is commonly used in training deep neural networks partly due to its practicability in relieving the exploding gradient problem.

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation

1 code implementation CVPR 2021 Liwei Wang, Jing Huang, Yin Li, Kun Xu, Zhengyuan Yang, Dong Yu

Our core innovation is the learning of a region-phrase score function, based on which an image-sentence score function is further constructed.

Contrastive Learning Knowledge Distillation +4

Deep Generative Modeling for Mechanistic-based Learning and Design of Metamaterial Systems

no code implementations27 Jun 2020 Liwei Wang, Yu-Chin Chan, Faez Ahmed, Zhao Liu, Ping Zhu, Wei Chen

For microstructure design, the tuning of mechanical properties and complex manipulations of microstructures are easily achieved by simple vector operations in the latent space.

Property Prediction

Data-Driven Topology Optimization with Multiclass Microstructures using Latent Variable Gaussian Process

no code implementations27 Jun 2020 Liwei Wang, Siyu Tao, Ping Zhu, Wei Chen

With this model, we can easily obtain a continuous and differentiable transition between different microstructure concepts that can render gradient information for multiscale topology optimization.

Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View.

no code implementations ICLR Workshop DeepDiffEq 2019 Yiping Lu*, Zhuohan Li*, Di He, Zhiqing Sun, Bin Dong, Tao Qin, LiWei Wang, Tie-Yan Liu

In particular, how words in a sentence are abstracted into contexts by passing through the layers of the Transformer can be interpreted as approximating multiple particles' movement in the space using the Lie-Trotter splitting scheme and the Euler's method.

Defective Convolutional Layers Learn Robust CNNs

no code implementations25 Sep 2019 Tiange Luo, Tianle Cai, Xiaomeng Zhang, Siyu Chen, Di He, LiWei Wang

We first show that predictions made by the defective CNN are less dependent on textural information, but more on shape information, and further find that adversarial examples generated by the defective CNN appear to have semantic shapes.

Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation

1 code implementation NeurIPS 2018 Liwei Wang, Lunjia Hu, Jiayuan Gu, Yue Wu, Zhiqiang Hu, Kun He, John Hopcroft

The theory gives a complete characterization of the structure of neuron activation subspace matches, where the core concepts are maximum match and simple match which describe the overall and the finest similarity between sets of neurons in two networks respectively.

Learning Two-Branch Neural Networks for Image-Text Matching Tasks

1 code implementation11 Apr 2017 Liwei Wang, Yin Li, Jing Huang, Svetlana Lazebnik

Image-language matching tasks have recently attracted a lot of attention in the computer vision field.

Image-text matching Retrieval +3

Learning Deep Structure-Preserving Image-Text Embeddings

no code implementations CVPR 2016 Liwei Wang, Yin Li, Svetlana Lazebnik

This paper proposes a method for learning joint embeddings of images and text using a two-branch neural network with multiple layers of linear projections followed by nonlinearities.

Image Retrieval Metric Learning +1

Training Deeper Convolutional Networks with Deep Supervision

1 code implementation11 May 2015 Liwei Wang, Chen-Yu Lee, Zhuowen Tu, Svetlana Lazebnik

One of the most promising ways of improving the performance of deep convolutional neural networks is by increasing the number of convolutional layers.

General Classification

Sufficient Conditions for Agnostic Active Learnable

no code implementations NeurIPS 2009 Liwei Wang

We study pool-based active learning in the presence of noise, i. e. the agnostic setting.

Active Learning General Classification

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