Search Results for author: Zi Wang

Found 67 papers, 23 papers with code

Transfer Learning for Bayesian Optimization on Heterogeneous Search Spaces

no code implementations28 Sep 2023 Zhou Fan, Xinran Han, Zi Wang

Bayesian optimization (BO) is a popular black-box function optimization method, which makes sequential decisions based on a Bayesian model, typically a Gaussian process (GP), of the function.

Bayesian Optimization Transfer Learning

A plug-and-play synthetic data deep learning for undersampled magnetic resonance image reconstruction

no code implementations13 Sep 2023 Min Xiao, Zi Wang, Jiefeng Guo, Xiaobo Qu

Magnetic resonance imaging (MRI) plays an important role in modern medical diagnostic but suffers from prolonged scan time.

De-aliasing MRI Reconstruction

HeroLT: Benchmarking Heterogeneous Long-Tailed Learning

1 code implementation17 Jul 2023 Haohui Wang, Weijie Guan, Jianpeng Chen, Zi Wang, Dawei Zhou

To achieve this, we develop the most comprehensive (to the best of our knowledge) long-tailed learning benchmark named HeroLT, which integrates 13 state-of-the-art algorithms and 6 evaluation metrics on 14 real-world benchmark datasets across 4 tasks from 3 domains.


On Evaluating Multilingual Compositional Generalization with Translated Datasets

1 code implementation20 Jun 2023 Zi Wang, Daniel Hershcovich

To address this limitation, we craft a faithful rule-based translation of the MCWQ dataset from English to Chinese and Japanese.

Machine Translation Semantic Parsing +1

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

no code implementations30 May 2023 Bailin Wang, Zi Wang, Xuezhi Wang, Yuan Cao, Rif A. Saurous, Yoon Kim

Large language models (LLMs) can learn to perform a wide range of natural language tasks from just a handful of in-context examples.

Semantic Parsing Text Generation

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

1 code implementation29 May 2023 Zi Wang, Alexander Ku, Jason Baldridge, Thomas L. Griffiths, Been Kim

Our experiments show it can (1) probe a model's representations of concepts even with a very small number of examples, (2) accurately measure both epistemic uncertainty (how confident the probe is) and aleatory uncertainty (how fuzzy the concepts are to the model), and (3) detect out of distribution data using those uncertainty measures as well as classic methods do.

Gaussian Processes

Rethink Diversity in Deep Learning Testing

no code implementations25 May 2023 Zi Wang, Jihye Choi, Somesh Jha

Deep neural networks (DNNs) have demonstrated extraordinary capabilities and are an integral part of modern software systems.

DNN Testing

Flare-Aware Cross-modal Enhancement Network for Multi-spectral Vehicle Re-identification

1 code implementation23 May 2023 Aihua Zheng, Zhiqi Ma, Zi Wang, Chenglong Li

Finally, to evaluate the proposed FACENet in handling intense flare, we introduce a new multi-spectral vehicle re-ID dataset, called WMVEID863, with additional challenges such as motion blur, significant background changes, and particularly intense flare degradation.

Vehicle Re-Identification

Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving

no code implementations24 Apr 2023 Shunli Ren, Zixing Lei, Zi Wang, Mehrdad Dianati, Yafei Wang, Siheng Chen, Wenjun Zhang

To achieve comprehensive recovery, we design a communication adaptive multi-scale spatial-temporal prediction model to extract multi-scale spatial-temporal features based on V2X communication conditions and capture the most significant information for the prediction of the missing information.

Autonomous Driving Knowledge Distillation

Efficient Symbolic Reasoning for Neural-Network Verification

no code implementations23 Mar 2023 Zi Wang, Somesh Jha, Krishnamurthy, Dvijotham

They allow us to encode many verification problems for neural networks as quadratic programs.

TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving

no code implementations CVPR 2023 Shaoheng Fang, Zi Wang, Yiqi Zhong, Junhao Ge, Siheng Chen, Yanfeng Wang

Second, a spatial-temporal pyramid transformer is introduced to comprehensively extract multi-scale BEV features and predict future BEV states with the support of spatial-temporal priors.

Autonomous Driving

Oriented Object Detection in Optical Remote Sensing Images using Deep Learning: A Survey

no code implementations21 Feb 2023 Kun Wang, Zi Wang, Zhang Li, Ang Su, Xichao Teng, Minhao Liu, Qifeng Yu

Oriented object detection is one of the most fundamental and challenging tasks in remote sensing, aiming at locating the oriented objects of numerous predefined object categories.

object-detection Object Detection +1

Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraints

no code implementations23 Dec 2022 Zi Wang, Minglin Chen, Yulan Guo, Zhang Li, Qifeng Yu

Recently, unsupervised domain adaptation in satellite pose estimation has gained increasing attention, aiming at alleviating the annotation cost for training deep models.

Pose Estimation Pseudo Label +1

HyperBO+: Pre-training a universal prior for Bayesian optimization with hierarchical Gaussian processes

1 code implementation20 Dec 2022 Zhou Fan, Xinran Han, Zi Wang

However, those prior learning methods typically assume that the input domains are the same for all tasks, weakening their ability to use observations on functions with different domains or generalize the learned priors to BO on different search spaces.

Bayesian Optimization Gaussian Processes +1

CloudBrain-ReconAI: An Online Platform for MRI Reconstruction and Image Quality Evaluation

no code implementations4 Dec 2022 Yirong Zhou, Chen Qian, Jiayu Li, Zi Wang, Yu Hu, Biao Qu, Liuhong Zhu, Jianjun Zhou, Taishan Kang, Jianzhong Lin, Qing Hong, Jiyang Dong, Di Guo, Xiaobo Qu

Efficient collaboration between engineers and radiologists is important for image reconstruction algorithm development and image quality evaluation in magnetic resonance imaging (MRI).

Cloud Computing MRI Reconstruction

A Faithful Deep Sensitivity Estimation for Accelerated Magnetic Resonance Imaging

no code implementations23 Oct 2022 Zi Wang, Haoming Fang, Chen Qian, Boxuan Shi, Lijun Bao, Liuhong Zhu, Jianjun Zhou, Wenping Wei, Jianzhong Lin, Di Guo, Xiaobo Qu

To understand the behavior of the network, the mutual promotion of sensitivity estimation and image reconstruction is revealed through the visualization of network intermediate results.

MRI Reconstruction

Parallel Augmentation and Dual Enhancement for Occluded Person Re-identification

no code implementations11 Oct 2022 Zi Wang, Huaibo Huang, Aihua Zheng, Chenglong Li, Ran He

To alleviate the above problems, we propose a simple but effective method with Parallel Augmentation and Dual Enhancement (PADE) that is robust on both occluded and non-occluded data, and does not require any auxiliary clues.

Person Re-Identification

Pre-training helps Bayesian optimization too

1 code implementation7 Jul 2022 Zi Wang, George E. Dahl, Kevin Swersky, Chansoo Lee, Zelda Mariet, Zachary Nado, Justin Gilmer, Jasper Snoek, Zoubin Ghahramani

Contrary to a common belief that BO is suited to optimizing black-box functions, it actually requires domain knowledge on characteristics of those functions to deploy BO successfully.

Bayesian Optimization

Towards Learning Universal Hyperparameter Optimizers with Transformers

1 code implementation26 May 2022 Yutian Chen, Xingyou Song, Chansoo Lee, Zi Wang, Qiuyi Zhang, David Dohan, Kazuya Kawakami, Greg Kochanski, Arnaud Doucet, Marc'Aurelio Ranzato, Sagi Perel, Nando de Freitas

Meta-learning hyperparameter optimization (HPO) algorithms from prior experiments is a promising approach to improve optimization efficiency over objective functions from a similar distribution.

Hyperparameter Optimization Meta-Learning

A Paired Phase and Magnitude Reconstruction for Advanced Diffusion-Weighted Imaging

no code implementations28 Mar 2022 Chen Qian, Zi Wang, Xinlin Zhang, Boxuan Shi, Boyu Jiang, Ran Tao, Jing Li, Yuwei Ge, Taishan Kang, Jianzhong Lin, Di Guo, Xiaobo Qu

Conclusion: The explicit phase model PAIR with complementary priors has a good performance on challenging reconstructions under inter-shot motions between shots and a low signal-to-noise ratio.

A Quantitative Geometric Approach to Neural-Network Smoothness

1 code implementation2 Mar 2022 Zi Wang, Gautam Prakriya, Somesh Jha

In this work, we provide a unified theoretical framework, a quantitative geometric approach, to address the Lipschitz constant estimation.

Onsite Non-Line-of-Sight Imaging via Online Calibrations

no code implementations29 Dec 2021 Zhengqing Pan, Ruiqian Li, Tian Gao, Zi Wang, Ping Liu, Siyuan Shen, Tao Wu, Jingyi Yu, Shiying Li

There has been an increasing interest in deploying non-line-of-sight (NLOS) imaging systems for recovering objects behind an obstacle.

One-dimensional Deep Low-rank and Sparse Network for Accelerated MRI

no code implementations9 Dec 2021 Zi Wang, Chen Qian, Di Guo, Hongwei Sun, Rushuai Li, Bo Zhao, Xiaobo Qu

Deep learning has shown astonishing performance in accelerated magnetic resonance imaging (MRI).

Pre-trained Gaussian processes for Bayesian optimization

4 code implementations16 Sep 2021 Zi Wang, George E. Dahl, Kevin Swersky, Chansoo Lee, Zachary Nado, Justin Gilmer, Jasper Snoek, Zoubin Ghahramani

Contrary to a common expectation that BO is suited to optimizing black-box functions, it actually requires domain knowledge about those functions to deploy BO successfully.

Bayesian Optimization Gaussian Processes

Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model

1 code implementation7 Jun 2021 Zi Wang

Here we propose the concept of decision-based black-box (DB3) knowledge distillation, with which the student is trained by distilling the knowledge from a black-box teacher (parameters are not accessible) that only returns classes rather than softmax outputs.

Knowledge Distillation

XCloud-pFISTA: A Medical Intelligence Cloud for Accelerated MRI

no code implementations18 Apr 2021 Yirong Zhou, Chen Qian, Yi Guo, Zi Wang, Jian Wang, Biao Qu, Di Guo, Yongfu You, Xiaobo Qu

Machine learning and artificial intelligence have shown remarkable performance in accelerated magnetic resonance imaging (MRI).

Cloud Computing Image Reconstruction

Data-Free Knowledge Distillation with Soft Targeted Transfer Set Synthesis

no code implementations10 Apr 2021 Zi Wang

Knowledge distillation (KD) has proved to be an effective approach for deep neural network compression, which learns a compact network (student) by transferring the knowledge from a pre-trained, over-parameterized network (teacher).

Knowledge Distillation Neural Network Compression

Convolutional Neural Network Pruning with Structural Redundancy Reduction

no code implementations CVPR 2021 Zi Wang, Chengcheng Li, Xiangyang Wang

Based on this finding, we then propose a network pruning approach that identifies structural redundancy of a CNN and prunes filters in the selected layer(s) with the most redundancy.

Network Pruning

Engineering the light coupling between metalens and photonic crystal resonators for robust on-chip microsystems

no code implementations9 Mar 2021 Yahui Xiao, Zi Wang, Feifan Wang, Hwaseob Lee, Thomas Kananen, Tingyi Gu

We designed an on-chip transformative optic system of a metalens-photonic crystal resonator metasystem on a foundry compatible silicon photonic platform.


Exploring Adversarial Robustness of Deep Metric Learning

1 code implementation14 Feb 2021 Thomas Kobber Panum, Zi Wang, Pengyu Kan, Earlence Fernandes, Somesh Jha

Deep Metric Learning (DML), a widely-used technique, involves learning a distance metric between pairs of samples.

Adversarial Robustness Metric Learning

Magnetic Resonance Spectroscopy Deep Learning Denoising Using Few In Vivo Data

no code implementations26 Jan 2021 Dicheng Chen, Wanqi Hu, Huiting Liu, Yirong Zhou, Tianyu Qiu, Yihui Huang, Zi Wang, Jiazheng Wang, Liangjie Lin, Zhigang Wu, Hao Chen, Xi Chen, Gen Yan, Di Guo, Jianzhong Lin, Xiaobo Qu

A deep learning model, Refusion Long Short-Term Memory (ReLSTM), was designed to learn the mapping from the low SNR time-domain data (24 SA) to the high SNR one (128 SA).


Non-line-of-Sight Imaging via Neural Transient Fields

1 code implementation2 Jan 2021 Siyuan Shen, Zi Wang, Ping Liu, Zhengqing Pan, Ruiqian Li, Tian Gao, Shiying Li, Jingyi Yu

We present a neural modeling framework for Non-Line-of-Sight (NLOS) imaging.

Generalized Universal Approximation for Certified Networks

no code implementations1 Jan 2021 Zi Wang, Aws Albarghouthi, Somesh Jha

To certify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using interval bound propagation.

Adversarial Deep Metric Learning

no code implementations1 Jan 2021 Thomas Kobber Panum, Zi Wang, Pengyu Kan, Earlence Fernandes, Somesh Jha

To the best of our knowledge, we are the first to systematically analyze this dependence effect and propose a principled approach for robust training of deep metric learning networks that accounts for the nuances of metric losses.

Metric Learning

Exponential Signal Reconstruction with Deep Hankel Matrix Factorization

no code implementations13 Jul 2020 Yihui Huang, Jinkui Zhao, Zi Wang, Vladislav Orekhov, Di Guo, Xiaobo Qu

Exponential is a basic signal form, and how to fast acquire this signal is one of the fundamental problems and frontiers in signal processing.

Rolling Shutter Correction

Interval Universal Approximation for Neural Networks

no code implementations12 Jul 2020 Zi Wang, Aws Albarghouthi, Gautam Prakriya, Somesh Jha

This is a crucial question, as our constructive proof of IUA is exponential in the size of the approximation domain.

TOFU: Target-Oriented FUzzer

no code implementations29 Apr 2020 Zi Wang, Ben Liblit, Thomas Reps

TOFU is also input-structure aware (i. e., the search makes use of a specification of a superset of the program's allowed inputs).

Software Engineering

Semantic Robustness of Models of Source Code

1 code implementation7 Feb 2020 Goutham Ramakrishnan, Jordan Henkel, Zi Wang, Aws Albarghouthi, Somesh Jha, Thomas Reps

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions.

Review and Prospect: Deep Learning in Nuclear Magnetic Resonance Spectroscopy

no code implementations13 Jan 2020 Dicheng Chen, Zi Wang, Di Guo, Vladislav Orekhov, Xiaobo Qu

In this Minireview, we summarize applications of DL in Nuclear Magnetic Resonance (NMR) spectroscopy and outline a perspective for DL as entirely new approaches that are likely to transform NMR spectroscopy into a much more efficient and powerful technique in chemistry and life science.

Investigating Channel Pruning through Structural Redundancy Reduction -- A Statistical Study

no code implementations16 May 2019 Chengcheng Li, Zi Wang, Dali Wang, Xiangyang Wang, Hairong Qi

Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction errors after pruning.

Single-shot Channel Pruning Based on Alternating Direction Method of Multipliers

no code implementations18 Feb 2019 Chengcheng Li, Zi Wang, Xiangyang Wang, Hairong Qi

In this work, we propose a novel single-shot channel pruning approach based on alternating direction methods of multipliers (ADMM), which can eliminate the need for complex iterative pruning and fine-tuning procedure and achieve a target compression ratio with only one run of pruning and fine-tuning.

General Classification Network Pruning

Speeding up convolutional networks pruning with coarse ranking

no code implementations18 Feb 2019 Zi Wang, Chengcheng Li, Dali Wang, Xiangyang Wang, Hairong Qi

In specific, with the proposed method, 75% and 54% of the total computation time for the whole pruning procedure can be reduced for AlexNet on CIFAR-10, and for VGG-16 on ImageNet, respectively.

Learning sparse relational transition models

no code implementations ICLR 2019 Victoria Xia, Zi Wang, Leslie Pack Kaelbling

For any action, a rule selects a set of relevant objects and computes a distribution over properties of just those objects in the resulting state given their properties in the previous state.

Learning to guide task and motion planning using score-space representation

no code implementations26 Jul 2018 Beomjoon Kim, Zi Wang, Leslie Pack Kaelbling, Tomas Lozano-Perez

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems.

Motion Planning

Fast-converging Conditional Generative Adversarial Networks for Image Synthesis

no code implementations5 May 2018 Chengcheng Li, Zi Wang, Hairong Qi

Building on top of the success of generative adversarial networks (GANs), conditional GANs attempt to better direct the data generation process by conditioning with certain additional information.

Image Generation

Active model learning and diverse action sampling for task and motion planning

2 code implementations2 Mar 2018 Zi Wang, Caelan Reed Garrett, Leslie Pack Kaelbling, Tomás Lozano-Pérez

Solving long-horizon problems in complex domains requires flexible generative planning that can combine primitive abilities in novel combinations to solve problems as they arise in the world.

Active Learning Motion Planning

Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis

no code implementations14 Jan 2018 Zi Wang, Dali Wang, Chengcheng Li, Yichi Xu, Husheng Li, Zhirong Bao

However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulation networks at the right scales.

reinforcement-learning Reinforcement Learning (RL)

Batched Large-scale Bayesian Optimization in High-dimensional Spaces

2 code implementations5 Jun 2017 Zi Wang, Clement Gehring, Pushmeet Kohli, Stefanie Jegelka

Bayesian optimization (BO) has become an effective approach for black-box function optimization problems when function evaluations are expensive and the optimum can be achieved within a relatively small number of queries.

Bayesian Optimization Vocal Bursts Intensity Prediction

Max-value Entropy Search for Efficient Bayesian Optimization

4 code implementations ICML 2017 Zi Wang, Stefanie Jegelka

We propose a new criterion, Max-value Entropy Search (MES), that instead uses the information about the maximum function value.

Focused Model-Learning and Planning for Non-Gaussian Continuous State-Action Systems

no code implementations26 Jul 2016 Zi Wang, Stefanie Jegelka, Leslie Pack Kaelbling, Tomás Lozano-Pérez

We introduce a framework for model learning and planning in stochastic domains with continuous state and action spaces and non-Gaussian transition models.

Studying the brain from adolescence to adulthood through sparse multi-view matrix factorisations

no code implementations9 May 2016 Zi Wang, Vyacheslav Karolis, Chiara Nosarti, Giovanni Montana

These latent factors can be used to produce low-dimensional visualisations of the data that emphasise age-specific effects once the shared effects have been accounted for.

Optimization as Estimation with Gaussian Processes in Bandit Settings

1 code implementation21 Oct 2015 Zi Wang, Bolei Zhou, Stefanie Jegelka

Recently, there has been rising interest in Bayesian optimization -- the optimization of an unknown function with assumptions usually expressed by a Gaussian Process (GP) prior.

Bayesian Optimization Gaussian Processes

Sparse multi-view matrix factorisation: a multivariate approach to multiple tissue comparisons

no code implementations4 Mar 2015 Zi Wang, Wei Yuan, Giovanni Montana

The proposed methodology can be interpreted as an extension of principal component analysis in that it provides the means to decompose the total sample variance in each tissue into the sum of two components: one capturing the variance that is shared across tissues, and one isolating the tissue-specific variances.

An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization

no code implementations30 Sep 2014 Necdet Serhat Aybat, Garud Iyengar, Zi Wang

We propose a distributed first-order augmented Lagrangian (DFAL) algorithm to minimize the sum of composite convex functions, where each term in the sum is a private cost function belonging to a node, and only nodes connected by an edge can directly communicate with each other.

Optimization and Control

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