Search Results for author: Miao Zhang

Found 57 papers, 25 papers with code

Perception of Misalignment States for Sky Survey Telescopes with the Digital Twin and the Deep Neural Networks

no code implementations30 Nov 2023 Miao Zhang, Peng Jia, Zhengyang Li, Wennan Xiang, Jiameng Lv, Rui Sun

To address this, we need a method to obtain misalignment states, aiding in the reconstruction of accurate point spread functions for data processing methods or facilitating adjustments of optical components for improved image quality.


Automatic Instruction Optimization for Open-source LLM Instruction Tuning

1 code implementation22 Nov 2023 Yilun Liu, Shimin Tao, Xiaofeng Zhao, Ming Zhu, Wenbing Ma, Junhao Zhu, Chang Su, Yutai Hou, Miao Zhang, Min Zhang, Hongxia Ma, Li Zhang, Hao Yang, Yanfei Jiang

However, the manual creation of high-quality instruction datasets is costly, leading to the adoption of automatic generation of instruction pairs by LLMs as a popular alternative in the training of open-source LLMs.

Instruction Following

Asymmetrically Decentralized Federated Learning

no code implementations8 Oct 2023 Qinglun Li, Miao Zhang, Nan Yin, Quanjun Yin, Li Shen

To further improve algorithm performance and alleviate local heterogeneous overfitting in Federated Learning (FL), our algorithm combines the Sharpness Aware Minimization (SAM) optimizer and local momentum.

Federated Learning

Deep Model Fusion: A Survey

no code implementations27 Sep 2023 Weishi Li, Yong Peng, Miao Zhang, Liang Ding, Han Hu, Li Shen

Specifically, we categorize existing deep model fusion methods as four-fold: (1) "Mode connectivity", which connects the solutions in weight space via a path of non-increasing loss, in order to obtain better initialization for model fusion; (2) "Alignment" matches units between neural networks to create better conditions for fusion; (3) "Weight average", a classical model fusion method, averages the weights of multiple models to obtain more accurate results closer to the optimal solution; (4) "Ensemble learning" combines the outputs of diverse models, which is a foundational technique for improving the accuracy and robustness of the final model.

Ensemble Learning

ILCAS: Imitation Learning-Based Configuration-Adaptive Streaming for Live Video Analytics with Cross-Camera Collaboration

no code implementations19 Aug 2023 Duo Wu, Dayou Zhang, Miao Zhang, Ruoyu Zhang, Fangxin Wang, Shuguang Cui

The high-accuracy and resource-intensive deep neural networks (DNNs) have been widely adopted by live video analytics (VA), where camera videos are streamed over the network to resource-rich edge/cloud servers for DNN inference.

Imitation Learning

A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendations

1 code implementation13 Aug 2023 Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi

Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage resources.

Adversarial Robustness Network Pruning +1

Influence Function Based Second-Order Channel Pruning-Evaluating True Loss Changes For Pruning Is Possible Without Retraining

1 code implementation13 Aug 2023 Hongrong Cheng, Miao Zhang, Javen Qinfeng Shi

It motivates us to develop a technique to evaluate true loss changes without retraining, with which channels to prune can be selected more reliably and confidently.

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

1 code implementation NeurIPS 2023 Xin Zheng, Miao Zhang, Chunyang Chen, Quoc Viet Hung Nguyen, Xingquan Zhu, Shirui Pan

Specifically, SFGC contains two collaborative components: (1) a training trajectory meta-matching scheme for effectively synthesizing small-scale graph-free data; (2) a graph neural feature score metric for dynamically evaluating the quality of the condensed data.

Graph Learning

Physics-Assisted Reduced-Order Modeling for Identifying Dominant Features of Transonic Buffet

no code implementations23 May 2023 Jing Wang, Hairun Xie, Miao Zhang, Hui Xu

The dominant latent space further reveals a strong relevance with the key flow features located in the boundary layers downstream of shock.

SCRNet: a Retinex Structure-based Low-light Enhancement Model Guided by Spatial Consistency

no code implementations14 May 2023 Miao Zhang, Yiqing Shen, Shenghui Zhong

Images captured under low-light conditions are often plagued by several challenges, including diminished contrast, increased noise, loss of fine details, and unnatural color reproduction.

Image Segmentation Low-Light Image Enhancement +3

Knowledge-embedded meta-learning model for lift coefficient prediction of airfoils

no code implementations6 Mar 2023 Hairun Xie, Jing Wang, Miao Zhang

In the proposed model, a primary network is responsible for representing the relationship between the lift and angle of attack, while the geometry information is encoded into a hyper network to predict the unknown parameters involved in the primary network.


LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version

1 code implementation24 Feb 2023 David Campos, Miao Zhang, Bin Yang, Tung Kieu, Chenjuan Guo, Christian S. Jensen

First, we propose adaptive ensemble distillation that assigns adaptive weights to different base models such that their varying classification capabilities contribute purposefully to the training of the lightweight model.

Classification Decision Making +4

Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs

no code implementations23 Feb 2023 Xin Zheng, Miao Zhang, Chunyang Chen, Qin Zhang, Chuan Zhou, Shirui Pan

Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities.

Graph Learning Neural Architecture Search

AutoPINN: When AutoML Meets Physics-Informed Neural Networks

no code implementations8 Dec 2022 Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Shuai Zhao, Yi Zhang, Huai Wang, Bin Yang

We then propose a resource-aware search strategy to explore the search space to find the best PINN model under different resource constraints.


Joint Neural Architecture and Hyperparameter Search for Correlated Time Series Forecasting

no code implementations29 Nov 2022 Xinle Wu, Dalin Zhang, Miao Zhang, Chenjuan Guo, Bin Yang, Christian S. Jensen

To overcome these limitations, we propose SEARCH, a joint, scalable framework, to automatically devise effective CTS forecasting models.

Correlated Time Series Forecasting Time Series

Fair contrastive pre-training for geographic image segmentation

no code implementations16 Nov 2022 Miao Zhang, Rumi Chunara

Contrastive self-supervised learning is widely employed in visual recognition for geographic image data (remote or proximal sensing), but because of landscape heterogeneity, models can show disparate performance across spatial units.

Contrastive Learning Fairness +4

SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters

1 code implementation9 Oct 2022 Shwai He, Liang Ding, Daize Dong, Miao Zhang, DaCheng Tao

Adapter Tuning, which freezes the pretrained language models (PLMs) and only fine-tunes a few extra modules, becomes an appealing efficient alternative to the full model fine-tuning.

Network Pruning

FedHiSyn: A Hierarchical Synchronous Federated Learning Framework for Resource and Data Heterogeneity

no code implementations21 Jun 2022 Guanghao Li, Yue Hu, Miao Zhang, Ji Liu, Quanjun Yin, Yong Peng, Dejing Dou

As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects.

Federated Learning

Parametric Generative Schemes with Geometric Constraints for Encoding and Synthesizing Airfoils

no code implementations5 May 2022 Hairun Xie, Jing Wang, Miao Zhang

In contrast, the hard-constrained scheme produces airfoils with a wider range of geometric diversity while strictly adhering to the geometric constraints.

Segmenting across places: The need for fair transfer learning with satellite imagery

no code implementations9 Apr 2022 Miao Zhang, Harvineet Singh, Lazarus Chok, Rumi Chunara

This work highlights the need to conduct fairness analysis for satellite imagery segmentation models and motivates the development of methods for fair transfer learning in order not to introduce disparities between places, particularly urban and rural locations.

Fairness Image Segmentation +4

Graph Neural Networks for Graphs with Heterophily: A Survey

no code implementations14 Feb 2022 Xin Zheng, Yixin Liu, Shirui Pan, Miao Zhang, Di Jin, Philip S. Yu

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriads of graph analytic tasks and applications.

MFNet: Multi-filter Directive Network for Weakly Supervised Salient Object Detection

1 code implementation ICCV 2021 Yongri Piao, Jian Wang, Miao Zhang, Huchuan Lu

The multiple accurate cues from multiple DFs are then simultaneously propagated to the saliency network with a multi-guidance loss.

object-detection Object Detection +2

BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule

no code implementations CVPR 2022 Miao Zhang, Jilin Hu, Steven Su, Shirui Pan, Xiaojun Chang, Bin Yang, Gholamreza Haffari

Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.

Neural Architecture Search Variational Inference

MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning

no code implementations30 Oct 2021 Miao Zhang, Miaojing Shi, Li Li

Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image.

Few-Shot Semantic Segmentation Image Classification +3

Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation

no code implementations8 Oct 2021 Shengran Hu, Ran Cheng, Cheng He, Zhichao Lu, Jing Wang, Miao Zhang

For the goal of automated design of high-performance deep convolutional neural networks (CNNs), Neural Architecture Search (NAS) methodology is becoming increasingly important for both academia and industries. Due to the costly stochastic gradient descent (SGD) training of CNNs for performance evaluation, most existing NAS methods are computationally expensive for real-world deployments.

Neural Architecture Search

To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection

no code implementations4 Sep 2021 Yongri Piao, Jian Wang, Miao Zhang, Zhengxuan Ma, Huchuan Lu

Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate matches between image-level annotations and salient objects are still inadequate.

object-detection Object Detection +2

SplitAVG: A heterogeneity-aware federated deep learning method for medical imaging

1 code implementation6 Jul 2021 Miao Zhang, Liangqiong Qu, Praveer Singh, Jayashree Kalpathy-Cramer, Daniel L. Rubin

In this study, we propose a novel heterogeneity-aware federated learning method, SplitAVG, to overcome the performance drops from data heterogeneity in federated learning.

Binary Classification Federated Learning

Handling Data Heterogeneity with Generative Replay in Collaborative Learning for Medical Imaging

no code implementations24 Jun 2021 Liangqiong Qu, Niranjan Balachandar, Miao Zhang, Daniel Rubin

Specifically, instead of directly training a model for task performance, we develop a novel dual model architecture: a primary model learns the desired task, and an auxiliary "generative replay model" allows aggregating knowledge from the heterogenous clients.

Image Generation Privacy Preserving

Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis

no code implementations22 Jun 2021 Miao Zhang, Wei Huang, Li Wang

We investigate this question through the lens of edge connectivity, and provide an affirmative answer by defining a connectivity concept, ZERo-cost Operation Sensitivity (ZEROS), to score the importance of candidate operations in DARTS at initialization.

Network Pruning Neural Architecture Search

iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients

1 code implementation21 Jun 2021 Miao Zhang, Steven Su, Shirui Pan, Xiaojun Chang, Ehsan Abbasnejad, Reza Haffari

A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation.

Neural Architecture Search

Calibrated RGB-D Salient Object Detection

1 code implementation CVPR 2021 Wei Ji, Jingjing Li, Shuang Yu, Miao Zhang, Yongri Piao, Shunyu Yao, Qi Bi, Kai Ma, Yefeng Zheng, Huchuan Lu, Li Cheng

Complex backgrounds and similar appearances between objects and their surroundings are generally recognized as challenging scenarios in Salient Object Detection (SOD).

object-detection RGB-D Salient Object Detection +2

Dynamic Fusion Network For Light Field Depth Estimation

no code implementations13 Apr 2021 Yongri Piao, Yukun Zhang, Miao Zhang, Xinxin Ji

Focus based methods have shown promising results for the task of depth estimation.

Depth Estimation

Learning Multi-modal Information for Robust Light Field Depth Estimation

1 code implementation13 Apr 2021 Yongri Piao, Xinxin Ji, Miao Zhang, Yukun Zhang

We first excavate the internal spatial correlation by designing a context reasoning unit which separately extracts comprehensive contextual information from the focal stack and RGB images.

Depth Estimation

A Unified Framework for IRS Enabled Wireless Powered Sensor Networks

no code implementations19 Mar 2021 Zheng Chu, Zhengyu Zhu, Miao Zhang, Fuhui Zhou, Li Zhen, Xueqian Fu, and Naofal Al-Dhahir

To evaluate the performance of this IRS assisted WPSN, we are interested in maximizing its system sum throughput to jointly optimize the energy beamforming of the PS, the transmission time allocation, as well as the phase shifts of the WET and WIT phases.

Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective

no code implementations ICLR 2022 Wei Huang, Yayong Li, Weitao Du, Jie Yin, Richard Yi Da Xu, Ling Chen, Miao Zhang

Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.

DUT-LFSaliency: Versatile Dataset and Light Field-to-RGB Saliency Detection

no code implementations30 Dec 2020 Yongri Piao, Zhengkun Rong, Shuang Xu, Miao Zhang, Huchuan Lu

The success of learning-based light field saliency detection is heavily dependent on how a comprehensive dataset can be constructed for higher generalizability of models, how high dimensional light field data can be effectively exploited, and how a flexible model can be designed to achieve versatility for desktop computers and mobile devices.

Saliency Detection

Differentiable Neural Architecture Search in Equivalent Space with Exploration Enhancement

1 code implementation NeurIPS 2020 Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, ZongYuan Ge, Steven Su

A probabilistic exploration enhancement method is accordingly devised to encourage intelligent exploration during the architecture search in the latent space, to avoid local optimal in architecture search.

Bilevel Optimization Neural Architecture Search

Real-time Earthquake Early Warning with Deep Learning: Application to the 2016 Central Apennines, Italy Earthquake Sequence

no code implementations2 Jun 2020 Xiong Zhang, Miao Zhang, Xiao Tian

Earthquake early warning systems are required to report earthquake locations and magnitudes as quickly as possible before the damaging S wave arrival to mitigate seismic hazards.

Overcoming Multi-Model Forgetting in One-Shot NAS With Diversity Maximization

1 code implementation CVPR 2020 Miao Zhang, Huiqi Li, Shirui Pan, Xiaojun Chang, Steven Su

In this paper, we formulate the supernet training in the One-Shot NAS as a constrained optimization problem of continual learning that the learning of current architecture should not degrade the performance of previous architectures during the supernet training.

Continual Learning Neural Architecture Search

Select, Supplement and Focus for RGB-D Saliency Detection

1 code implementation CVPR 2020 Miao Zhang, Weisong Ren, Yongri Piao, Zhengkun Rong, Huchuan Lu

Depth data containing a preponderance of discriminative power in location have been proven beneficial for accurate saliency prediction.

Ranked #15 on RGB-D Salient Object Detection on NJU2K (using extra training data)

RGB-D Salient Object Detection Saliency Prediction +1

Memory-oriented Decoder for Light Field Salient Object Detection

1 code implementation NeurIPS 2019 Miao Zhang, Jingjing Li, Ji Wei, Yongri Piao, Huchuan Lu

In this paper, we present a deep-learning-based method where a novel memory-oriented decoder is tailored for light field saliency detection.

object-detection RGB Salient Object Detection +2

Efficient Novelty-Driven Neural Architecture Search

no code implementations22 Jul 2019 Miao Zhang, Huiqi Li, Shirui Pan, Taoping Liu, Steven Su

The best architecture obtained by our algorithm with the same search space achieves the state-of-the-art test error rate of 2. 51\% on CIFAR-10 with only 7. 5 hours search time in a single GPU, and a validation perplexity of 60. 02 and a test perplexity of 57. 36 on PTB.

Neural Architecture Search Test

High Dimensional Bayesian Optimization via Supervised Dimension Reduction

1 code implementation21 Jul 2019 Miao Zhang, Huiqi Li, Steven Su

Furthermore, a kernel trick is developed to reduce computational complexity and learn nonlinear subset of the unknowing function when applying SIR to extremely high dimensional BO.

Bayesian Optimization Dimensionality Reduction +1

Multi-level CNN for lung nodule classification with Gaussian Process assisted hyperparameter optimization

1 code implementation2 Jan 2019 Miao Zhang, Huiqi Li, Juan Lyu, Sai Ho Ling, Steven Su

In this paper, a non-stationary kernel is proposed which allows the surrogate model to adapt to functions whose smoothness varies with the spatial location of inputs, and a multi-level convolutional neural network (ML-CNN) is built for lung nodule classification whose hyperparameter configuration is optimized by using the proposed non-stationary kernel based Gaussian surrogate model.

Bayesian Optimization Gaussian Processes +3

Ancient Painting to Natural Image: A New Solution for Painting Processing

1 code implementation2 Jan 2019 Tingting Qiao, Weijing Zhang, Miao Zhang, Zixuan Ma, Duanqing Xu

By doing so, the ancient painting processing problems become natural image processing problems and models trained on natural images can be directly applied to the transferred paintings.

Style Transfer Test

Land use mapping in the Three Gorges Reservoir Area based on semantic segmentation deep learning method

no code implementations18 Mar 2018 Xin Zhang, Bingfang Wu, Liang Zhu, Fuyou Tian, Miao Zhang, Yuanzeng

In this paper, we first test the state of the art semantic segmentation deep learning classifiers for LUCC mapping with 7 categories in the TGRA area with rapideye 5m resolution data.

Semantic Segmentation Test

Authorship attribution of source code by using back propagation neural network based on particle swarm optimization

1 code implementation PLOS ONE 2017 Xinyu Yang, Guoai Xu, Qi Li, Yanhui Guo, Miao Zhang

Then these metrics are input to neural network for supervised learning, the weights of which are output by PSO and BP hybrid algorithm.

Speaker Recognition with Cough, Laugh and "Wei"

no code implementations22 Jun 2017 Miao Zhang, Yixiang Chen, Lantian Li, Dong Wang

This paper proposes a speaker recognition (SRE) task with trivial speech events, such as cough and laugh.

Speaker Recognition

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