Search Results for author: Yue Wang

Found 255 papers, 97 papers with code

Sentence-Level Resampling for Named Entity Recognition

1 code implementation NAACL 2022 Xiaochen Wang, Yue Wang

As a fundamental task in natural language processing, named entity recognition (NER) aims to locate and classify named entities in unstructured text.

Data Augmentation named-entity-recognition +2

基于词信息嵌入的汉语构词结构识别研究(Chinese Word-Formation Prediction based on Representations of Word-Related Features)

no code implementations CCL 2021 Hua Zheng, Yaqi Yan, Yue Wang, Damai Dai, Yang Liu

“作为一种意合型语言, 汉语中的构词结构刻画了构词成分之间的组合关系, 是认知、理解词义的关键。在中文信息处理领域, 此前的构词结构识别工作大多沿用句法层面的粗粒度标签, 且主要基于上下文等词间信息建模, 忽略了语素义、词义等词内信息对构词结构识别的作用。本文采用语言学视域下的构词结构标签体系, 构建汉语构词结构及相关信息数据集, 提出了一种基于Bi-LSTM和Self-attention的模型, 以此来探究词内、词间等多方面信息对构词结构识别的潜在影响和能达到的性能。实验取得了良好的预测效果, 准确率77. 87%, F1值78. 36%;同时, 对比测试揭示, 词内的语素义信息对构词结构识别具有显著的贡献, 而词间的上下文信息贡献较弱且带有较强的不稳定性。该预测方法与数据集, 将为中文信息处理的多种任务, 如语素和词结构分析、词义识别与生成、语言文字研究与词典编纂等提供新的观点和方案。”

Rethinking Directional Integration in Neural Radiance Fields

no code implementations28 Nov 2023 Congyue Deng, Jiawei Yang, Leonidas Guibas, Yue Wang

To that end, we introduce a modification to the NeRF rendering equation which is as simple as a few lines of code change for any NeRF variations, while greatly improving the rendering quality of view-dependent effects.

3D Reconstruction Disentanglement +2

A Language Agent for Autonomous Driving

1 code implementation17 Nov 2023 Jiageng Mao, Junjie Ye, Yuxi Qian, Marco Pavone, Yue Wang

Our approach, termed Agent-Driver, transforms the traditional autonomous driving pipeline by introducing a versatile tool library accessible via function calls, a cognitive memory of common sense and experiential knowledge for decision-making, and a reasoning engine capable of chain-of-thought reasoning, task planning, motion planning, and self-reflection.

Autonomous Driving Common Sense Reasoning +3

Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning

no code implementations8 Nov 2023 Yao Zhu, Yuefeng Chen, Wei Wang, Xiaofeng Mao, Xiu Yan, Yue Wang, Zhigang Li, Wang Lu, Jindong Wang, Xiangyang Ji

Hence, we propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics.

Augmenting Lane Perception and Topology Understanding with Standard Definition Navigation Maps

no code implementations7 Nov 2023 Katie Z Luo, Xinshuo Weng, Yan Wang, Shuang Wu, Jie Li, Kilian Q Weinberger, Yue Wang, Marco Pavone

We propose a novel framework to integrate SD maps into online map prediction and propose a Transformer-based encoder, SD Map Encoder Representations from transFormers, to leverage priors in SD maps for the lane-topology prediction task.

Autonomous Driving Lane Detection

G-SPEED: General SParse Efficient Editing MoDel

1 code implementation16 Oct 2023 Haoke Zhang, Yue Wang, Juntao Li, Xiabing Zhou, Min Zhang

Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages.

GPT-Driver: Learning to Drive with GPT

1 code implementation2 Oct 2023 Jiageng Mao, Yuxi Qian, Junjie Ye, Hang Zhao, Yue Wang

In this paper, we propose a novel approach to motion planning that capitalizes on the strong reasoning capabilities and generalization potential inherent to Large Language Models (LLMs).

Autonomous Driving Decision Making +2

Sparsity-Based Channel Estimation Exploiting Deep Unrolling for Downlink Massive MIMO

no code implementations24 Sep 2023 An Chen, Wenbo Xu, Liyang Lu, Yue Wang

Massive multiple-input multiple-output (MIMO) enjoys great advantage in 5G wireless communication systems owing to its spectrum and energy efficiency.

Compressive Sensing

RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair

no code implementations12 Sep 2023 Weishi Wang, Yue Wang, Shafiq Joty, Steven C. H. Hoi

Automatic program repair (APR) is crucial to reduce manual debugging efforts for developers and improve software reliability.

Language Modelling Program Repair +1

RGAT: A Deeper Look into Syntactic Dependency Information for Coreference Resolution

1 code implementation10 Sep 2023 Yuan Meng, Xuhao Pan, Jun Chang, Yue Wang

Our experiments on a public Gendered Ambiguous Pronouns (GAP) dataset show that with the supervision learning of the syntactic dependency graph and without fine-tuning the entire BERT, we increased the F1-score of the previous best model (RGCN-with-BERT) from 80. 3% to 82. 5%, compared to the F1-score by single BERT embeddings from 78. 5% to 82. 5%.

coreference-resolution Graph Attention

Toward High Quality Facial Representation Learning

1 code implementation7 Sep 2023 Yue Wang, Jinlong Peng, Jiangning Zhang, Ran Yi, Liang Liu, Yabiao Wang, Chengjie Wang

To improve the facial representation quality, we use feature map of a pre-trained visual backbone as a supervision item and use a partially pre-trained decoder for mask image modeling.

Contrastive Learning Face Alignment +2

StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction

1 code implementation24 Aug 2023 Tianyuan Yuan, Yicheng Liu, Yue Wang, Yilun Wang, Hang Zhao

This approach limits their stability and performance in complex scenarios such as occlusions, largely due to the absence of temporal information.

Autonomous Driving

Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models

no code implementations24 Aug 2023 Yue Wang, Xinrui Wang, Juntao Li, Jinxiong Chang, Qishen Zhang, Zhongyi Liu, Guannan Zhang, Min Zhang

Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks.

Order-of-mutation effects on cancer progression: models for myeloproliferative neoplasm

no code implementations19 Aug 2023 Yue Wang, Blerta Shtylla, Tom Chou

In some patients with myeloproliferative neoplasms, two genetic mutations can be found, JAK2 V617F and TET2.

Exploiting Point-Wise Attention in 6D Object Pose Estimation Based on Bidirectional Prediction

no code implementations16 Aug 2023 Yuhao Yang, Jun Wu, Yue Wang, Guangjian Zhang, Rong Xiong

Traditional geometric registration based estimation methods only exploit the CAD model implicitly, which leads to their dependence on observation quality and deficiency to occlusion.

6D Pose Estimation using RGB

Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples

1 code implementation27 Jul 2023 Peng Li, Yeye He, Cong Yan, Yue Wang, Surajit Chaudhuri

Relational tables, where each row corresponds to an entity and each column corresponds to an attribute, have been the standard for tables in relational databases.

Joint Radio Frequency Fingerprints Identification via Multi-antenna Receiver

no code implementations11 Jul 2023 Xiaofang Chen, Wenbo Xu, Yue Wang

When the number is small, the Mutual Information Weighting Scheme (MIWS) is developed by calculating the weighted voting of RFFI result at each antenna; when the number is moderate, the Distortions Filtering Scheme (DFS) is developed by filtering out the channel noise and receiver distortions; when the number is large enough, the Group-Distortions Filtering and Weighting Scheme (GDFWS) is developed, which integrates the advantages of MIWS and DFS.

Privately generating tabular data using language models

1 code implementation7 Jun 2023 Alexandre Sablayrolles, Yue Wang, Brian Karrer

Privately generating synthetic data from a table is an important brick of a privacy-first world.

Language Modelling

An Empirical Study on Challenging Math Problem Solving with GPT-4

1 code implementation2 Jun 2023 Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang

Employing Large Language Models (LLMs) to address mathematical problems is an intriguing research endeavor, considering the abundance of math problems expressed in natural language across numerous science and engineering fields.

Elementary Mathematics Math

CodeTF: One-stop Transformer Library for State-of-the-art Code LLM

1 code implementation31 May 2023 Nghi D. Q. Bui, Hung Le, Yue Wang, Junnan Li, Akhilesh Deepak Gotmare, Steven C. H. Hoi

In this paper, we present CodeTF, an open-source Transformer-based library for state-of-the-art Code LLMs and code intelligence.

Leveraging BEV Representation for 360-degree Visual Place Recognition

1 code implementation23 May 2023 Xuecheng Xu, Yanmei Jiao, Sha Lu, Xiaqing Ding, Rong Xiong, Yue Wang

In addition, the image and point cloud cues can be easily stated in the same coordinates, which benefits sensor fusion for place recognition.

Sensor Fusion Visual Place Recognition

'Tax-free' 3DMM Conditional Face Generation

no code implementations22 May 2023 Yiwen Huang, Zhiqiu Yu, Xinjie Yi, Yue Wang, James Tompkin

This results in a new model that effectively removes the quality tax between 3DMM conditioned face GANs and the unconditional StyleGAN.

Face Generation

Achieving the Minimax Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach

no code implementations22 May 2023 Yue Wang, JinJun Xiong, Shaofeng Zou

We show that an improved sample complexity of $\mathcal{O}(SC^{\pi^*}\epsilon^{-2}(1-\gamma)^{-3})$ can be obtained, which matches with the minimax lower bound for offline reinforcement learning, and thus is minimax optimal.


Discounted Thompson Sampling for Non-Stationary Bandit Problems

no code implementations18 May 2023 Han Qi, Yue Wang, Li Zhu

Under mild assumptions, we show that DS-TS with Gaussian priors can achieve nearly optimal regret bound on the order of $\tilde{O}(\sqrt{TB_T})$ for abruptly changing and $\tilde{O}(T^{\beta})$ for smoothly changing, where $T$ is the number of time steps, $B_T$ is the number of breakpoints, $\beta$ is associated with the smoothly changing environment and $\tilde{O}$ hides the parameters independent of $T$ as well as logarithmic terms.

Thompson Sampling

Model-Free Robust Average-Reward Reinforcement Learning

no code implementations17 May 2023 Yue Wang, Alvaro Velasquez, George Atia, Ashley Prater-Bennette, Shaofeng Zou

Robust Markov decision processes (MDPs) address the challenge of model uncertainty by optimizing the worst-case performance over an uncertainty set of MDPs.

Q-Learning reinforcement-learning

GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training

1 code implementation CVPR 2023 Xiaoyu Tian, Haoxi Ran, Yue Wang, Hang Zhao

This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without annotations?

Multi-Object Tracking object-detection +3

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

1 code implementation13 May 2023 Yue Wang, Hung Le, Akhilesh Deepak Gotmare, Nghi D. Q. Bui, Junnan Li, Steven C. H. Hoi

To address these limitations, we propose ``CodeT5+'', a family of encoder-decoder LLMs for code in which component modules can be flexibly combined to suit a wide range of downstream code tasks.

Arithmetic Reasoning Code Completion +4

On Uni-Modal Feature Learning in Supervised Multi-Modal Learning

1 code implementation2 May 2023 Chenzhuang Du, Jiaye Teng, Tingle Li, Yichen Liu, Tianyuan Yuan, Yue Wang, Yang Yuan, Hang Zhao

We abstract the features (i. e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions.

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

1 code implementation NeurIPS 2023 Xiaoyu Tian, Tao Jiang, Longfei Yun, Yucheng Mao, Huitong Yang, Yue Wang, Yilun Wang, Hang Zhao

3D occupancy prediction, which estimates the detailed occupancy states and semantics of a scene, is an emerging task to overcome these limitations.

Autonomous Driving

How to Control Hydrodynamic Force on Fluidic Pinball via Deep Reinforcement Learning

1 code implementation23 Apr 2023 Haodong Feng, Yue Wang, Hui Xiang, Zhiyang Jin, Dixia Fan

The finding from this work can control hydrodynamic force on the operation of fluidic pinball system and potentially pave the way for exploring efficient active flow control strategies in other complex fluid dynamic problems.

Decision Making reinforcement-learning +2

Neural Map Prior for Autonomous Driving

no code implementations CVPR 2023 Xuan Xiong, Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, Hang Zhao

To the best of our knowledge, this is the first learning-based system for creating a global map prior.

Autonomous Driving Navigate

How Does Imperfect Automatic Indexing Affect Semantic Search Performance?

no code implementations8 Apr 2023 Mengtian Guo, David Gotz, Yue Wang

In this work, we aim to understand the performance impact of using imperfectly assigned terms in Boolean semantic searches.

Simplifying Low-Light Image Enhancement Networks with Relative Loss Functions

1 code implementation6 Apr 2023 Yu Zhang, Xiaoguang Di, Junde Wu, Rao Fu, Yong Li, Yue Wang, Yanwu Xu, Guohui YANG, Chunhui Wang

In this paper, to make the learning easier in low-light image enhancement, we introduce FLW-Net (Fast and LightWeight Network) and two relative loss functions.

Low-Light Image Enhancement

Object-centric Inference for Language Conditioned Placement: A Foundation Model based Approach

no code implementations6 Apr 2023 Zhixuan Xu, Kechun Xu, Yue Wang, Rong Xiong

We focus on the task of language-conditioned object placement, in which a robot should generate placements that satisfy all the spatial relational constraints in language instructions.

UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields

no code implementations ICCV 2023 Yuanbo Yang, Yifei Yang, Hanlei Guo, Rong Xiong, Yue Wang, Yiyi Liao

Generating photorealistic images with controllable camera pose and scene contents is essential for many applications including AR/VR and simulation.

3D-Aware Image Synthesis

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

no code implementations24 Mar 2023 Yue Wang, Wending Li, Michail Maniatakos, Saif Eddin Jabari

The effectiveness of the proposed method is verified on a simulated traffic system based on a microscopic traffic simulator, where experimental results showcase that the smoothed traffic controller can neutralize all trigger samples and maintain the performance of relieving traffic congestion

Autonomous Vehicles Image Classification

Physical Backdoor Trigger Activation of Autonomous Vehicle using Reachability Analysis

no code implementations24 Mar 2023 Wenqing Li, Yue Wang, Muhammad Shafique, Saif Eddin Jabari

Recent studies reveal that Autonomous Vehicles (AVs) can be manipulated by hidden backdoors, causing them to perform harmful actions when activated by physical triggers.

Autonomous Vehicles

GOOD: General Optimization-based Fusion for 3D Object Detection via LiDAR-Camera Object Candidates

no code implementations17 Mar 2023 Bingqi Shen, Shuwei Dai, Yuyin Chen, Rong Xiong, Yue Wang, Yanmei Jiao

In this paper, we propose GOOD, a general optimization-based fusion framework that can achieve satisfying detection without training additional models and is available for any combinations of 2D and 3D detectors to improve the accuracy and robustness of 3D detection.

3D Object Detection Autonomous Driving +1

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

2 code implementations CVPR 2023 Jiawei Yang, Marco Pavone, Yue Wang

One is to regularize the frequency range of NeRF's inputs, while the other is to penalize the near-camera density fields.

Neural Rendering Novel View Synthesis

Efficient Gridless DoA Estimation Method of Non-uniform Linear Arrays with Applications in Automotive Radars

no code implementations8 Mar 2023 Silin Gao, Zhe Zhang, Muhan Wang, Yan Zhang, Jie Zhao, Bingchen Zhang, Yue Wang, Yirong Wu

This paper focuses on the gridless direction-of-arrival (DoA) estimation for data acquired by non-uniform linear arrays (NLAs) in automotive applications.

AERK: Aligned Entropic Reproducing Kernels through Continuous-time Quantum Walks

no code implementations4 Mar 2023 Lixin Cui, Ming Li, Yue Wang, Lu Bai, Edwin R. Hancock

For pairwise graphs, the proposed AERK kernel is defined by computing a reproducing kernel based similarity between the quantum Shannon entropies of their each pair of aligned vertices.

Graph Classification

Multimodal Industrial Anomaly Detection via Hybrid Fusion

1 code implementation CVPR 2023 Yue Wang, Jinlong Peng, Jiangning Zhang, Ran Yi, Yabiao Wang, Chengjie Wang

2D-based Industrial Anomaly Detection has been widely discussed, however, multimodal industrial anomaly detection based on 3D point clouds and RGB images still has many untouched fields.

Ranked #2 on RGB+3D Anomaly Detection and Segmentation on MVTEC 3D-AD (using extra training data)

Contrastive Learning RGB+3D Anomaly Detection and Segmentation

NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition

no code implementations20 Feb 2023 Xinquan Huang, Wenlei Shi, Qi Meng, Yue Wang, Xiaotian Gao, Jia Zhang, Tie-Yan Liu

Neural networks have shown great potential in accelerating the solution of partial differential equations (PDEs).

GRAFS: Graphical Faceted Search System to Support Conceptual Understanding in Exploratory Search

no code implementations19 Feb 2023 Mengtian Guo, Zhilan Zhou, David Gotz, Yue Wang

When people search for information about a new topic within large document collections, they implicitly construct a mental model of the unfamiliar information space to represent what they currently know and guide their exploration into the unknown.

Mathematical models for order of mutation problem in myeloproliferative neoplasm: non-additivity and non-commutativity

no code implementations16 Feb 2023 Yue Wang

In some patients of myeloproliferative neoplasm, two genetic mutations can be found: JAK2 V617F and TET2.

Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation

1 code implementation10 Feb 2023 Rui Zhang, Qi Meng, Rongchan Zhu, Yue Wang, Wenlei Shi, Shihua Zhang, Zhi-Ming Ma, Tie-Yan Liu

To address these limitations, we propose the Monte Carlo Neural PDE Solver (MCNP Solver) for training unsupervised neural solvers via the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles.

GE-Blender: Graph-Based Knowledge Enhancement for Blender

no code implementations30 Jan 2023 Xiaolei Lian, Xunzhu Tang, Yue Wang

Although the great success of open-domain dialogue generation, unseen entities can have a large impact on the dialogue generation task.

Dialogue Generation TAG

Three facets of mathematical cancer biology research

no code implementations24 Jan 2023 Yue Wang

In this review, we will discuss three mathematical approaches for studying cancer biology: population dynamics, gene regulation, and developmental biology.

Using Fano factors to determine certain types of gene autoregulation

no code implementations17 Jan 2023 Yue Wang, Siqi He

These two propositions form a simple but robust method to infer the existence of autoregulation in certain scenarios from gene expression data.

Super-Resolution Harmonic Retrieval of Non-Circular Signals

no code implementations17 Jan 2023 Yu Zhang, Yue Wang, Zhi Tian, Geert Leus, Gong Zhang

This paper proposes a super-resolution harmonic retrieval method for uncorrelated strictly non-circular signals, whose covariance and pseudo-covariance present Toeplitz and Hankel structures, respectively.

Retrieval Super-Resolution

Cell Population Growth Kinetics in the Presence of Stochastic Heterogeneity of Cell Phenotype

no code implementations10 Jan 2023 Yue Wang, Joseph X. Zhou, Edoardo Pedrini, Irit Rubin, May Khalil, Roberto Taramelli, Hong Qian, Sui Huang

Recent studies at individual cell resolution have revealed phenotypic heterogeneity in nominally clonal tumor cell populations.

Algorithms for the uniqueness of the longest common subsequence

1 code implementation10 Jan 2023 Yue Wang

In this paper, we consider how to determine the uniqueness of the longest common subsequence.

Robust Average-Reward Markov Decision Processes

no code implementations2 Jan 2023 Yue Wang, Alvaro Velasquez, George Atia, Ashley Prater-Bennette, Shaofeng Zou

We derive the robust Bellman equation for robust average-reward MDPs, prove that the optimal policy can be derived from its solution, and further design a robust relative value iteration algorithm that provably finds its solution, or equivalently, the optimal robust policy.

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

no code implementations CVPR 2023 Sicheng Li, Hao Li, Yue Wang, Yiyi Liao, Lu Yu

Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering.

Novel View Synthesis

RPN: A Word Vector Level Data Augmentation Algorithm in Deep Learning for Language Understanding

1 code implementation12 Dec 2022 Zhengqing Yuan, Xiaolong Zhang, Yue Wang, Xuecong Hou, Huiwen Xue, Zhuanzhe Zhao, Yongming Liu

However, existing data augmentation techniques in natural language understanding (NLU) may not fully capture the complexity of natural language variations, and they can be challenging to apply to large datasets.

CoLA Natural Language Inference +5

FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification

1 code implementation11 Dec 2022 Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang

Weakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data.

text-classification Text Classification +1

ATASI-Net: An Efficient Sparse Reconstruction Network for Tomographic SAR Imaging with Adaptive Threshold

no code implementations30 Nov 2022 Muhan Wang, Zhe Zhang, Xiaolan Qiu, Silin Gao, Yue Wang

In addition, adaptive threshold is introduced for each azimuth-range pixel, enabling the threshold shrinkage to be not only layer-varied but also element-wise.


Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5

no code implementations27 Nov 2022 Nghi D. Q. Bui, Yue Wang, Steven Hoi

Specifically, we propose three objectives to adapt the generic CodeT5 for debugging: a bug detection objective to determine whether a given code snippet is buggy or not, a bug localization objective to identify the buggy lines, and a program repair objective to translate the buggy code to its fixed version.

Bug fixing Language Modelling +1

Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning

no code implementations21 Nov 2022 Zhongxiang Zhou, Yifei Yang, Yue Wang, Rong Xiong

To disambiguate unknown objects and background in the first subtask, we propose to use classification-free region proposal network (CF-RPN) which estimates the objectness score of each region purely using cues from object's location and shape preventing overfitting to the training categories.

Contrastive Learning object-detection +3

Compressive Spectrum Sensing Using Blind-Block Orthogonal Least Squares

no code implementations14 Nov 2022 Liyang Lu, Wenbo Xu, Yue Wang, Zhi Tian

In this paper, we propose a blind-block orthogonal least squares-based compressive spectrum sensing (B-BOLS-CSS) algorithm, which utilizes a novel blind stopping rule to cut the cords to these prior information.

Compressive Sensing

Compressive Spectrum Sensing Using Sampling-Controlled Block Orthogonal Matching Pursuit

no code implementations14 Nov 2022 Liyang Lu, Wenbo Xu, Yue Wang, Zhi Tian

To this end, the minimum number of required measurements for successful recovery is first derived in terms of its probabilistic lower bound.

HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification

no code implementations5 Nov 2022 Lu Bai, Lixin Cui, Yue Wang, Ming Li, Edwin R. Hancock

In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs.

Graph Classification

Downlink Massive MIMO Channel Estimation via Deep Unrolling : Sparsity Exploitations in Angular Domain

no code implementations31 Oct 2022 An Chen, Wenbo Xu, Liyang Lu, Yue Wang

In frequency division duplex (FDD) massive MIMO systems, reliable downlink channel estimation is essential for the subsequent data transmission but is realized at the cost of massive pilot overhead due to hundreds of antennas at base station (BS).

Compressive Sensing Rolling Shutter Correction

Efficient Wideband DoA Estimation with a Robust Iterative Method for Uniform Circular Arrays

no code implementations30 Oct 2022 Xiaorui Ding, Wenbo Xu, Yue Wang

The key parameters of the proposed method in the current iteration are adjusted based on the estimation results in the previous iterations.

Distributed Swarm Learning for Internet of Things at the Edge: Where Artificial Intelligence Meets Biological Intelligence

no code implementations29 Oct 2022 Yue Wang, Zhi Tian, Xin Fan, Yan Huo, Cameron Nowzari, Kai Zeng

With the proliferation of versatile Internet of Things (IoT) services, smart IoT devices are increasingly deployed at the edge of wireless networks to perform collaborative machine learning tasks using locally collected data, giving rise to the edge learning paradigm.

Robust Distributed Learning Against Both Distributional Shifts and Byzantine Attacks

no code implementations29 Oct 2022 Guanqiang Zhou, Ping Xu, Yue Wang, Zhi Tian

In this paper, we propose a new algorithm that equips distributed learning with robustness measures against both distributional shifts and byzantine attacks.

RING++: Roto-translation Invariant Gram for Global Localization on a Sparse Scan Map

1 code implementation12 Oct 2022 Xuecheng Xu, Sha Lu, Jun Wu, Haojian Lu, Qiuguo Zhu, Yiyi Liao, Rong Xiong, Yue Wang

In addition, we derive sufficient conditions of feature extractors for the representation preserving the roto-translation invariance, making RING++ a framework applicable to generic multi-channel features.


A Robust and Constrained Multi-Agent Reinforcement Learning Electric Vehicle Rebalancing Method in AMoD Systems

no code implementations17 Sep 2022 Sihong He, Yue Wang, Shuo Han, Shaofeng Zou, Fei Miao

In this work, we design a robust and constrained multi-agent reinforcement learning (MARL) framework with state transition kernel uncertainty for EV AMoD systems.

Fairness Multi-agent Reinforcement Learning +1

Robust Constrained Reinforcement Learning

no code implementations14 Sep 2022 Yue Wang, Fei Miao, Shaofeng Zou

We then investigate a concrete example of $\delta$-contamination uncertainty set, design an online and model-free algorithm and theoretically characterize its sample complexity.

Adversarial Attack reinforcement-learning +1

Finite-Time Error Bounds for Greedy-GQ

no code implementations6 Sep 2022 Yue Wang, Yi Zhou, Shaofeng Zou

Our techniques in this paper provide a general approach for finite-sample analysis of non-convex two timescale value-based reinforcement learning algorithms.

reinforcement-learning Reinforcement Learning (RL)

CB-DSL: Communication-efficient and Byzantine-robust Distributed Swarm Learning on Non-i.i.d. Data

no code implementations10 Aug 2022 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

data issues and Byzantine attacks, global data samples are introduced in CB-DSL and shared among IoT workers, which not only alleviates the local data heterogeneity effectively but also enables to fully utilize the exploration-exploitation mechanism of swarm intelligence.

QC-ODKLA: Quantized and Communication-Censored Online Decentralized Kernel Learning via Linearized ADMM

no code implementations4 Aug 2022 Ping Xu, Yue Wang, Xiang Chen, Zhi Tian

We then propose a novel learning framework named Online Decentralized Kernel learning via Linearized ADMM (ODKLA) to efficiently solve the online decentralized kernel learning problem.


ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queries

no code implementations CVPR 2023 Junru Gu, Chenxu Hu, Tianyuan Zhang, Xuanyao Chen, Yilun Wang, Yue Wang, Hang Zhao

In this work, we propose ViP3D, a query-based visual trajectory prediction pipeline that exploits rich information from raw videos to directly predict future trajectories of agents in a scene.

Autonomous Driving Trajectory Prediction

CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning

2 code implementations5 Jul 2022 Hung Le, Yue Wang, Akhilesh Deepak Gotmare, Silvio Savarese, Steven C. H. Hoi

To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL).

Code Generation Program Synthesis +2

Towards Two-view 6D Object Pose Estimation: A Comparative Study on Fusion Strategy

no code implementations1 Jul 2022 Jun Wu, Lilu Liu, Yue Wang, Rong Xiong

We ascertain the Mid- Fusion approach is the best approach to restore the most precise 3D keypoints useful for object pose estimation.

6D Pose Estimation using RGB

Predicting Stock Price Movement after Disclosure of Corporate Annual Reports: A Case Study of 2021 China CSI 300 Stocks

no code implementations25 Jun 2022 Fengyu Han, Yue Wang

We conclude that according to the financial indicators based on the just-released annual report of the company, the predictability of the stock price movement on the second day after disclosure is weak, with maximum accuracy about 59. 6% and maximum precision about 0. 56 on our test set by the random forest classifier, and the stock filtering does not improve the performance.

Stock Price Prediction

Deep Random Vortex Method for Simulation and Inference of Navier-Stokes Equations

no code implementations20 Jun 2022 Rui Zhang, Peiyan Hu, Qi Meng, Yue Wang, Rongchan Zhu, Bingguang Chen, Zhi-Ming Ma, Tie-Yan Liu

To this end, we propose the \emph{Deep Random Vortex Method} (DRVM), which combines the neural network with a random vortex dynamics system equivalent to the Navier-Stokes equation.

VectorMapNet: End-to-end Vectorized HD Map Learning

1 code implementation17 Jun 2022 Yicheng Liu, Tianyuan Yuan, Yue Wang, Yilun Wang, Hang Zhao

To the best of our knowledge, VectorMapNet is the first work designed towards end-to-end vectorized map learning from onboard observations.

3D Lane Detection Autonomous Driving +2

Collaborative Knowledge Graph Fusion by Exploiting the Open Corpus

no code implementations15 Jun 2022 Yue Wang, Yao Wan, Lu Bai, Lixin Cui, Zhuo Xu, Ming Li, Philip S. Yu, Edwin R Hancock

To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations.

Event Extraction Knowledge Graphs

MBGDT:Robust Mini-Batch Gradient Descent

2 code implementations14 Jun 2022 Hanming Wang, Haozheng Luo, Yue Wang

In high dimensions, most machine learning method perform fragile even there are a little outliers.


Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward

no code implementations13 Jun 2022 Tengyu Xu, Yue Wang, Shaofeng Zou, Yingbin Liang

The remarkable success of reinforcement learning (RL) heavily relies on observing the reward of every visited state-action pair.

Offline RL reinforcement-learning +1

DPCN++: Differentiable Phase Correlation Network for Versatile Pose Registration

no code implementations12 Jun 2022 Zexi Chen, Yiyi Liao, Haozhe Du, Haodong Zhang, Xuecheng Xu, Haojian Lu, Rong Xiong, Yue Wang

Next, the rotation, scale, and translation are independently and efficiently estimated in the spectrum step-by-step using the DPC solver.


Policy Gradient Method For Robust Reinforcement Learning

no code implementations15 May 2022 Yue Wang, Shaofeng Zou

We further develop a smoothed robust policy gradient method and show that to achieve an $\epsilon$-global optimum, the complexity is $\mathcal O(\epsilon^{-3})$.

reinforcement-learning Reinforcement Learning (RL)

Learning A Simulation-based Visual Policy for Real-world Peg In Unseen Holes

1 code implementation9 May 2022 Liang Xie, Hongxiang Yu, Kechun Xu, Tong Yang, Minhang Wang, Haojian Lu, Rong Xiong, Yue Wang

This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation, and adapting to arbitrary unseen shapes in real world with minimal sim-to-real cost.

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

no code implementations5 May 2022 Muhan Wang, Zhe Zhang, Yue Wang, Silin Gao, Xiaolan Qiu

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving three-dimensional reconstruction along the elevation direction from multiple observations.

3D Reconstruction Super-Resolution

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries

1 code implementation2 May 2022 Tianyuan Zhang, Xuanyao Chen, Yue Wang, Yilun Wang, Hang Zhao

In contrast to prior works, MUTR3D does not explicitly rely on the spatial and appearance similarity of objects.

Autonomous Driving Depth Estimation

Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs

1 code implementation13 Apr 2022 Peiyan Hu, Qi Meng, Bingguang Chen, Shiqi Gong, Yue Wang, Wei Chen, Rongchan Zhu, Zhi-Ming Ma, Tie-Yan Liu

Stochastic partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics.

Accurate Portraits of Scientific Resources and Knowledge Service Components

no code implementations11 Apr 2022 Yue Wang, Zhe Xue, Ang Li

With the advent of the cloud computing era, the cost of creating, capturing and managing information has gradually decreased.

Cloud Computing Management

Blind Orthogonal Least Squares based Compressive Spectrum Sensing

no code implementations11 Apr 2022 Liyang Lu, Wenbo Xu, Yue Wang, Zhi Tian

As an enabling technique of cognitive radio (CR), compressive spectrum sensing (CSS) based on compressive sensing (CS) can detect the spectrum opportunities from wide frequency bands efficiently and accurately by using sub-Nyquist sampling rate.

Compressive Sensing

A Visual Navigation Perspective for Category-Level Object Pose Estimation

1 code implementation25 Mar 2022 Jiaxin Guo, Fangxun Zhong, Rong Xiong, Yunhui Liu, Yue Wang, Yiyi Liao

In this paper, we take a deeper look at the inference of analysis-by-synthesis from the perspective of visual navigation, and investigate what is a good navigation policy for this specific task.

Imitation Learning Pose Estimation +1

Academic Resource Text Level Multi-label Classification based on Attention

no code implementations21 Mar 2022 Yue Wang, Yawen Li, Ang Li

We propose an attention-based hierarchical multi-label classification algorithm of academic texts (AHMCA) by integrating features such as text, keywords, and hierarchical structure, the academic documents are classified into the most relevant categories.

Document Embedding Hierarchical Multi-label Classification +2

FUTR3D: A Unified Sensor Fusion Framework for 3D Detection

1 code implementation20 Mar 2022 Xuanyao Chen, Tianyuan Zhang, Yue Wang, Yilun Wang, Hang Zhao

Sensor fusion is an essential topic in many perception systems, such as autonomous driving and robotics.

Autonomous Driving Sensor Fusion

PiDAn: A Coherence Optimization Approach for Backdoor Attack Detection and Mitigation in Deep Neural Networks

no code implementations17 Mar 2022 Yue Wang, Wenqing Li, Esha Sarkar, Muhammad Shafique, Michail Maniatakos, Saif Eddin Jabari

Based on our theoretical analysis and experimental results, we demonstrate the effectiveness of PiDAn in defending against backdoor attacks that use different settings of poisoned samples on GTSRB and ILSVRC2012 datasets.

Anomaly Detection Backdoor Attack

CtlGAN: Few-shot Artistic Portraits Generation with Contrastive Transfer Learning

no code implementations16 Mar 2022 Yue Wang, Ran Yi, Ying Tai, Chengjie Wang, Lizhuang Ma

We propose a new encoder which embeds real faces into Z+ space and proposes a dual-path training strategy to better cope with the adapted decoder and eliminate the artifacts.

Image-to-Image Translation Transfer Learning

Translation Invariant Global Estimation of Heading Angle Using Sinogram of LiDAR Point Cloud

no code implementations2 Mar 2022 Xiaqing Ding, Xuecheng Xu, Sha Lu, Yanmei Jiao, Mengwen Tan, Rong Xiong, Huanjun Deng, Mingyang Li, Yue Wang

Global point cloud registration is an essential module for localization, of which the main difficulty exists in estimating the rotation globally without initial value.

Point Cloud Registration Translation

Inference on autoregulation in gene expression

no code implementations10 Jan 2022 Yue Wang, Siqi He

These two propositions form a simple but robust method to infer the existence of autoregulation from gene expression data.

Writing Style Aware Document-level Event Extraction

no code implementations10 Jan 2022 Zhuo Xu, Yue Wang, Lu Bai, Lixin Cui

This verifies the writing style contains valuable information that could improve the performance of the event extraction task.

Document-level Event Extraction Event Extraction +1

Robust factored principal component analysis for matrix-valued outlier accommodation and detection

no code implementations13 Dec 2021 Xuan Ma, Jianhua Zhao, Yue Wang

To solve the robustness problem suffered by FPCA and make it applicable to matrix data, in this paper we propose a robust extension of FPCA (RFPCA), which is built upon a $t$-type distribution called matrix-variate $t$ distribution.

Dimensionality Reduction Outlier Detection

Auto-Tag: Tagging-Data-By-Example in Data Lakes

no code implementations11 Dec 2021 Yeye He, Jie Song, Yue Wang, Surajit Chaudhuri, Vishal Anil, Blake Lassiter, Yaron Goland, Gaurav Malhotra

As data lakes become increasingly popular in large enterprises today, there is a growing need to tag or classify data assets (e. g., files and databases) in data lakes with additional metadata (e. g., semantic column-types), as the inferred metadata can enable a range of downstream applications like data governance (e. g., GDPR compliance), and dataset search.


Transformer-based Network for RGB-D Saliency Detection

no code implementations1 Dec 2021 Yue Wang, Xu Jia, Lu Zhang, Yuke Li, James Elder, Huchuan Lu

TFFM conducts a sufficient feature fusion by integrating features from multiple scales and two modalities over all positions simultaneously.

Saliency Detection

Weakly Supervised Prototype Topic Model with Discriminative Seed Words: Modifying the Category Prior by Self-exploring Supervised Signals

no code implementations20 Nov 2021 Bing Wang, Yue Wang, Ximing Li, Jihong Ouyang

The recent generative dataless methods construct document-specific category priors by using seed word occurrences only, however, such category priors often contain very limited and even noisy supervised signals.

text-classification Text Classification +1

EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text Generation

1 code implementation30 Oct 2021 Anthony Colas, Ali Sadeghian, Yue Wang, Daisy Zhe Wang

We also evaluate two types of baseline on EventNarrative: a graph-to-text specific model and two state-of-the-art language models, which previous work has shown to be adaptable to the knowledge graph-to-text domain.

KG-to-Text Generation Knowledge Graphs +2

BEV-SGD: Best Effort Voting SGD for Analog Aggregation Based Federated Learning against Byzantine Attackers

no code implementations18 Oct 2021 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

As a promising distributed learning technology, analog aggregation based federated learning over the air (FLOA) provides high communication efficiency and privacy provisioning under the edge computing paradigm.

Edge-computing Federated Learning

Object DGCNN: 3D Object Detection using Dynamic Graphs

1 code implementation NeurIPS 2021 Yue Wang, Justin Solomon

Our method models 3D object detection as message passing on a dynamic graph, generalizing the DGCNN framework to predict a set of objects.

3D Object Detection Autonomous Driving +2

Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework

1 code implementation13 Oct 2021 Lu Mi, Tianxing He, Core Francisco Park, Hao Wang, Yue Wang, Nir Shavit

In this work, we show how data labeled with semantically continuous attributes can be utilized to conduct a quantitative evaluation of latent-space interpolation algorithms, for variational autoencoders.

DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries

1 code implementation13 Oct 2021 Yue Wang, Vitor Guizilini, Tianyuan Zhang, Yilun Wang, Hang Zhao, Justin Solomon

This top-down approach outperforms its bottom-up counterpart in which object bounding box prediction follows per-pixel depth estimation, since it does not suffer from the compounding error introduced by a depth prediction model.

3D Object Detection Autonomous Driving +4

Machine Translation Verbosity Control for Automatic Dubbing

no code implementations8 Oct 2021 Surafel M. Lakew, Marcello Federico, Yue Wang, Cuong Hoang, Yogesh Virkar, Roberto Barra-Chicote, Robert Enyedi

Automatic dubbing aims at seamlessly replacing the speech in a video document with synthetic speech in a different language.

Machine Translation Translation

Are BERT Families Zero-Shot Learners? A Study on Their Potential and Limitations

no code implementations29 Sep 2021 Yue Wang, Lijun Wu, Xiaobo Liang, Juntao Li, Min Zhang

Starting from the resurgence of deep learning, language models (LMs) have never been so popular.

Online Robust Reinforcement Learning with Model Uncertainty

no code implementations NeurIPS 2021 Yue Wang, Shaofeng Zou

In this paper, we focus on model-free robust RL, where the uncertainty set is defined to be centering at a misspecified MDP that generates a single sample trajectory sequentially and is assumed to be unknown.

Q-Learning reinforcement-learning +1

Learning Interpretable BEV Based VIO without Deep Neural Networks

no code implementations25 Sep 2021 Zexi Chen, Haozhe Du, Xuecheng Xu, Rong Xiong, Yiyi Liao, Yue Wang

Specifically, we first adopt Unscented Kalman Filter as a differentiable layer to predict the pitch and roll, where the covariance matrices of noise are learned to filter out the noise of the IMU raw data.

Autonomous Driving Pose Estimation

Learning Stereopsis from Geometric Synthesis for 6D Object Pose Estimation

no code implementations25 Sep 2021 Jun Wu, Lilu Liu, Yue Wang, Rong Xiong

Current monocular-based 6D object pose estimation methods generally achieve less competitive results than RGBD-based methods, mostly due to the lack of 3D information.

6D Pose Estimation using RGB

Domain Generalization for Vision-based Driving Trajectory Generation

1 code implementation22 Sep 2021 Yunkai Wang, Dongkun Zhang, Yuxiang Cui, Zexi Chen, Wei Jing, Junbo Chen, Rong Xiong, Yue Wang

In this paper, we propose a domain generalization method for vision-based driving trajectory generation for autonomous vehicles in urban environments, which can be seen as a solution to extend the Invariant Risk Minimization (IRM) method in complex problems.

Autonomous Vehicles Domain Generalization

CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation

5 code implementations EMNLP 2021 Yue Wang, Weishi Wang, Shafiq Joty, Steven C. H. Hoi

We present CodeT5, a unified pre-trained encoder-decoder Transformer model that better leverages the code semantics conveyed from the developer-assigned identifiers.

Clone Detection Code Summarization +4

A framework for massive scale personalized promotion

no code implementations27 Aug 2021 Yitao Shen, Yue Wang, Xingyu Lu, Feng Qi, Jia Yan, Yixiang Mu, Yao Yang, Yifan Peng, Jinjie Gu

In order to do effective optimization in the second stage, counterfactual prediction and noise-reduction are essential for the first stage.


Inference on the structure of gene regulatory networks

no code implementations27 Jul 2021 Yue Wang, Zikun Wang

For scenarios that have not been covered in literature, if the structure can be inferred, we propose new mathematical inference methods and evaluate them on simulated data.

HDMapNet: An Online HD Map Construction and Evaluation Framework

2 code implementations13 Jul 2021 Qi Li, Yue Wang, Yilun Wang, Hang Zhao

By introducing the method and metrics, we invite the community to study this novel map learning problem.

Autonomous Driving HD semantic map learning

Improving Multi-Modal Learning with Uni-Modal Teachers

no code implementations21 Jun 2021 Chenzhuang Du, Tingle Li, Yichen Liu, Zixin Wen, Tianyu Hua, Yue Wang, Hang Zhao

We name this problem Modality Failure, and hypothesize that the imbalance of modalities and the implicit bias of common objectives in fusion method prevent encoders of each modality from sufficient feature learning.

Image Segmentation Semantic Segmentation

Improved Radar Localization on Lidar Maps Using Shared Embedding

no code implementations18 Jun 2021 Huan Yin, Yue Wang, Rong Xiong

We present a heterogeneous localization framework for solving radar global localization and pose tracking on pre-built lidar maps.

Pose Tracking Retrieval

Incorporating NODE with Pre-trained Neural Differential Operator for Learning Dynamics

no code implementations8 Jun 2021 Shiqi Gong, Qi Meng, Yue Wang, Lijun Wu, Wei Chen, Zhi-Ming Ma, Tie-Yan Liu

In this paper, to reduce the reliance on the numerical solver, we propose to enhance the supervised signal in the training of NODE.

Feature-based Style Randomization for Domain Generalization

no code implementations6 Jun 2021 Yue Wang, Lei Qi, Yinghuan Shi, Yang Gao

As a recent noticeable topic, domain generalization (DG) aims to first learn a generic model on multiple source domains and then directly generalize to an arbitrary unseen target domain without any additional adaption.

Data Augmentation Domain Generalization

Towards Modeling the Style of Translators in Neural Machine Translation

no code implementations NAACL 2021 Yue Wang, Cuong Hoang, Marcello Federico

We show that our style-augmented translation models are able to capture the style variations of translators and to generate translations with different styles on new data.

Machine Translation Translation

Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic

3 code implementations12 May 2021 Dong Chen, Mohammad Hajidavalloo, Zhaojian Li, Kaian Chen, Yongqiang Wang, Longsheng Jiang, Yue Wang

On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs).

Autonomous Vehicles reinforcement-learning +1

On Feature Decorrelation in Self-Supervised Learning

1 code implementation ICCV 2021 Tianyu Hua, Wenxiao Wang, Zihui Xue, Sucheng Ren, Yue Wang, Hang Zhao

In self-supervised representation learning, a common idea behind most of the state-of-the-art approaches is to enforce the robustness of the representations to predefined augmentations.

Representation Learning Self-Supervised Learning

Joint Optimization of Communications and Federated Learning Over the Air

no code implementations8 Apr 2021 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

Federated learning (FL) is an attractive paradigm for making use of rich distributed data while protecting data privacy.

Federated Learning

Non-Asymptotic Analysis for Two Time-scale TDC with General Smooth Function Approximation

no code implementations NeurIPS 2021 Yue Wang, Shaofeng Zou, Yi Zhou

Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning.

reinforcement-learning Reinforcement Learning (RL)

1-Bit Compressive Sensing for Efficient Federated Learning Over the Air

no code implementations30 Mar 2021 Xin Fan, Yue Wang, Yan Huo, Zhi Tian

For distributed learning among collaborative users, this paper develops and analyzes a communication-efficient scheme for federated learning (FL) over the air, which incorporates 1-bit compressive sensing (CS) into analog aggregation transmissions.

Compressive Sensing Dimensionality Reduction +3

HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark

1 code implementation19 Mar 2021 Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Yingyan Lin

To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance of all the networks in the search spaces of both NAS-Bench-201 and FBNet, on six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).

Hardware Aware Neural Architecture Search Neural Architecture Search

Efficient learning of goal-oriented push-grasping synergy in clutter

1 code implementation9 Mar 2021 Kechun Xu, Hongxiang Yu, Qianen Lai, Yue Wang, Rong Xiong

In this paper, a goal-conditioned hierarchical reinforcement learning formulation with high sample efficiency is proposed to learn a push-grasping policy for grasping a specific object in clutter.

Hierarchical Reinforcement Learning Robotics

Learn to Differ: Sim2Real Small Defection Segmentation Network

1 code implementation7 Mar 2021 Zexi Chen, Zheyuan Huang, Yunkai Wang, Xuecheng Xu, Yue Wang, Rong Xiong

In this paper, we propose the network SSDS that learns a way of distinguishing small defections between two images regardless of the context, so that the network can be trained once for all.

Collaborative Recognition of Feasible Region with Aerial and Ground Robots through DPCN

no code implementations1 Mar 2021 Yunshuang Li, Zheyuan Huang, Zexi Chen, Yue Wang, Rong Xiong

Taking the aerial robots' advantages of having large scale variance of view points of the same route which the ground robots is on, the collaboration work provides global information of road segmentation for the ground robot, thus enabling it to obtain feasible region and adjust its pose ahead of time.

Road Segmentation

Using Prior Knowledge to Guide BERT's Attention in Semantic Textual Matching Tasks

1 code implementation22 Feb 2021 Tingyu Xia, Yue Wang, Yuan Tian, Yi Chang

We study the problem of incorporating prior knowledge into a deep Transformer-based model, i. e., Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks.

Radar-to-Lidar: Heterogeneous Place Recognition via Joint Learning

1 code implementation30 Jan 2021 Huan Yin, Xuecheng Xu, Yue Wang, Rong Xiong

Place recognition is critical for both offline mapping and online localization.

SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training

1 code implementation4 Jan 2021 Xiaohan Chen, Yang Zhao, Yue Wang, Pengfei Xu, Haoran You, Chaojian Li, Yonggan Fu, Yingyan Lin, Zhangyang Wang

Results show that: 1) applied to inference, SD achieves up to 2. 44x energy efficiency as evaluated via real hardware implementations; 2) applied to training, SD leads to 10. 56x and 4. 48x reduction in the storage and training energy, with negligible accuracy loss compared to state-of-the-art training baselines.

HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark

no code implementations ICLR 2021 Chaojian Li, Zhongzhi Yu, Yonggan Fu, Yongan Zhang, Yang Zhao, Haoran You, Qixuan Yu, Yue Wang, Cong Hao, Yingyan Lin

To design HW-NAS-Bench, we carefully collected the measured/estimated hardware performance (e. g., energy cost and latency) of all the networks in the search space of both NAS-Bench-201 and FBNet, considering six hardware devices that fall into three categories (i. e., commercial edge devices, FPGA, and ASIC).

Hardware Aware Neural Architecture Search Neural Architecture Search

SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam

1 code implementation ICCV 2021 Yonggan Fu, Yang Zhang, Yue Wang, Zhihan Lu, Vivek Boominathan, Ashok Veeraraghavan, Yingyan Lin

PhlatCam, with its form factor potentially reduced by orders of magnitude, has emerged as a promising solution to the first aforementioned challenge, while the second one remains a bottleneck.

Benchmarking Model Compression +1

FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training

1 code implementation NeurIPS 2020 Yonggan Fu, Haoran You, Yang Zhao, Yue Wang, Chaojian Li, Kailash Gopalakrishnan, Zhangyang Wang, Yingyan Lin

Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due to the limited resources available at the edge and the required massive training costs for state-of-the-art (SOTA) DNNs.


3D Point-to-Keypoint Voting Network for 6D Pose Estimation

no code implementations22 Dec 2020 Weitong Hua, Jiaxin Guo, Yue Wang, Rong Xiong

In this paper, we propose a framework for 6D pose estimation from RGB-D data based on spatial structure characteristics of 3D keypoints.

6D Pose Estimation

CORAL: Colored structural representation for bi-modal place recognition

no code implementations22 Nov 2020 Yiyuan Pan, Xuecheng Xu, Weijie Li, Yunxiang Cui, Yue Wang, Rong Xiong

In this way, we fuse the structural features and visual features in the consistent bird-eye view frame, yielding a semantic representation, namely CORAL.

Visual Place Recognition

Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings

1 code implementation EMNLP 2020 Yue Wang, Jing Li, Michael R. Lyu, Irwin King

Further analyses show that our multi-head attention is able to attend information from various aspects and boost classification or generation in diverse scenarios.

PREGAN: Pose Randomization and Estimation for Weakly Paired Image Style Translation

1 code implementation31 Oct 2020 Zexi Chen, Jiaxin Guo, Xuecheng Xu, Yunkai Wang, Yue Wang, Rong Xiong

Utilizing the trained model under different conditions without data annotation is attractive for robot applications.

object-detection Object Detection +4

Self-supervised Representation Learning for Evolutionary Neural Architecture Search

1 code implementation31 Oct 2020 Chen Wei, Yiping Tang, Chuang Niu, Haihong Hu, Yue Wang, Jimin Liang

To enhance the predictive performance of neural predictors, we devise two self-supervised learning methods from different perspectives to pre-train the architecture embedding part of neural predictors to generate a meaningful representation of neural architectures.

Contrastive Learning Neural Architecture Search +2

Improving the generalization of network based relative pose regression: dimension reduction as a regularizer

no code implementations24 Oct 2020 Xiaqing Ding, Yue Wang, Li Tang, Yanmei Jiao, Rong Xiong

Through experiments on real world RGBD datasets we validate the effectiveness of our design in terms of improving both generalization performance and robustness towards viewpoint change, and also show the potential of regression based visual localization networks towards challenging occasions that are difficult for geometry based visual localization methods.

3D Reconstruction Dimensionality Reduction +3

DiSCO: Differentiable Scan Context with Orientation

1 code implementation21 Oct 2020 Xuecheng Xu, Huan Yin, Zexi Chen, Yue Wang, Rong Xiong

In this paper, we propose a LiDAR-based place recognition method, named Differentiable Scan Context with Orientation (DiSCO), which simultaneously finds the scan at a similar place and estimates their relative orientation.

Pose Estimation Robot Navigation

Imitation Learning of Hierarchical Driving Model: from Continuous Intention to Continuous Trajectory

2 code implementations20 Oct 2020 Yunkai Wang, Dongkun Zhang, Jingke Wang, Zexi Chen, Yue Wang, Rong Xiong

One of the challenges to reduce the gap between the machine and the human level driving is how to endow the system with the learning capacity to deal with the coupled complexity of environments, intentions, and dynamics.


Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks

no code implementations13 Oct 2020 Yue Wang, Zhuo Xu, Lu Bai, Yao Wan, Lixin Cui, Qian Zhao, Edwin R. Hancock, Philip S. Yu

To verify the effectiveness of our proposed method, we conduct extensive experiments on four real-world datasets as well as compare our method with state-of-the-art methods.

Event Extraction TAG

Inference on tissue transplantation experiments

no code implementations6 Oct 2020 Yue Wang, Boyu Zhang, Jérémie Kropp, Nadya Morozova

This method can provide the most probable results of a group of experiments or the probability of a specific result for each experiment.

Multi-Frame to Single-Frame: Knowledge Distillation for 3D Object Detection

no code implementations24 Sep 2020 Yue Wang, Alireza Fathi, Jiajun Wu, Thomas Funkhouser, Justin Solomon

A common dilemma in 3D object detection for autonomous driving is that high-quality, dense point clouds are only available during training, but not testing.

3D Object Detection Autonomous Driving +2

Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product

2 code implementations EMNLP 2020 Tiangang Zhu, Yue Wang, Haoran Li, Youzheng Wu, Xiaodong He, Bo-Wen Zhou

We annotate a multimodal product attribute value dataset that contains 87, 194 instances, and the experimental results on this dataset demonstrate that explicitly modeling the relationship between attributes and values facilitates our method to establish the correspondence between them, and selectively utilizing visual product information is necessary for the task.

Attribute Value Extraction Retrieval

RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model

1 code implementation15 Sep 2020 Huan Yin, Runjian Chen, Yue Wang, Rong Xiong

In this paper, we propose an end-to-end deep learning framework for Radar Localization on Lidar Map (RaLL) to bridge the gap, which not only achieves the robust radar localization but also exploits the mature lidar mapping technique, thus reducing the cost of radar mapping.

Synergistic saliency and depth prediction for RGB-D saliency detection

no code implementations3 Jul 2020 Yue Wang, Yuke Li, James H. Elder, Huchuan Lu, Runmin Wu, Lu Zhang

Evaluation on seven RGB-D datasets demonstrates that even without saliency ground truth for RGB-D datasets and using only the RGB data of RGB-D datasets at inference, our semi-supervised system performs favorable against state-of-the-art fully-supervised RGB-D saliency detection methods that use saliency ground truth for RGB-D datasets at training and depth data at inference on two largest testing datasets.

Depth Estimation Depth Prediction +1

Learning hierarchical behavior and motion planning for autonomous driving

1 code implementation8 May 2020 Jingke Wang, Yue Wang, Dongkun Zhang, Yezhou Yang, Rong Xiong

To improve the tactical decision-making for learning-based driving solution, we introduce hierarchical behavior and motion planning (HBMP) to explicitly model the behavior in learning-based solution.

Autonomous Driving Decision Making +2

SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation

no code implementations7 May 2020 Yang Zhao, Xiaohan Chen, Yue Wang, Chaojian Li, Haoran You, Yonggan Fu, Yuan Xie, Zhangyang Wang, Yingyan Lin

We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs).

Model Compression Quantization