Search Results for author: LiWei Wang

Found 64 papers, 25 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

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 implementation5 Apr 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

Multi-View Transformer for 3D Visual Grounding

1 code implementation5 Apr 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

2 code implementations28 Mar 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

Learning Physics-Informed Neural Networks without Stacked Back-propagation

no code implementations18 Feb 2022 Di He, Wenlei Shi, Shanda Li, Xiaotian Gao, Jia Zhang, Jiang Bian, LiWei Wang, Tie-Yan Liu

Physics-Informed Neural Network (PINN) has become a commonly used machine learning approach to solve partial differential equations (PDE).

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.

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

no code implementations1 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

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 +2

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 Visual Navigation

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

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

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

no code implementations21 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

DAGN: Discourse-Aware Graph Network for Logical Reasoning

1 code implementation 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.

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

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

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.

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

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.

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

5 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 Cityscapes val (PQst 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

no code implementations 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 +3

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.

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.

Text Matching Visual Grounding

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.