Search Results for author: Tao Huang

Found 49 papers, 17 papers with code

Improving Privacy Guarantee and Efficiency of Latent Dirichlet Allocation Model Training Under Differential Privacy

no code implementations Findings (EMNLP) 2021 Tao Huang, Hong Chen

To improve the privacy guarantee and efficiency, we combine a subsampling method with CGS and propose a novel LDA training algorithm with differential privacy, SUB-LDA.

FreeKD: Knowledge Distillation via Semantic Frequency Prompt

no code implementations20 Nov 2023 Yuan Zhang, Tao Huang, Jiaming Liu, Tao Jiang, Kuan Cheng, Shanghang Zhang

(2) During the distillation period, a pixel-wise frequency mask is generated via Frequency Prompt, to localize those pixel of interests (PoIs) in various frequency bands.

Knowledge Distillation

Unpaired MRI Super Resolution with Self-Supervised Contrastive Learning

no code implementations24 Oct 2023 Hao Li, Quanwei Liu, Jianan Liu, Xiling Liu, Yanni Dong, Tao Huang, Zhihan Lv

High-resolution (HR) magnetic resonance imaging (MRI) is crucial for enhancing diagnostic accuracy in clinical settings.

Contrastive Learning Image Super-Resolution

V2X Cooperative Perception for Autonomous Driving: Recent Advances and Challenges

no code implementations5 Oct 2023 Tao Huang, Jianan Liu, Xi Zhou, Dinh C. Nguyen, Mostafa Rahimi Azghadi, Yuxuan Xia, Qing-Long Han, Sumei Sun

To address this gap, this paper provides a comprehensive overview of the evolution of CP technologies, spanning from early explorations to recent developments, including advancements in V2X communication technologies.

Autonomous Driving Object Recognition

Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections

1 code implementation18 Sep 2023 Ting Meng, Chunyun Fu, Mingguang Huang, Xiyang Wang, JiaWei He, Tao Huang, Wankai Shi

However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified.

Multi-Object Tracking

Implicit Neural Representation for MRI Parallel Imaging Reconstruction

no code implementations12 Sep 2023 Hao Li, Yusheng Zhou, Jianan Liu, Xiling Liu, Tao Huang, Zhihan Lv

In this paper, we propose a novel MRI PI reconstruction method based on INR, which represents the reconstructed fully-sampled images as the function of voxel coordinates and prior feature vectors of undersampled images to overcome the generalization problem of INR.

MRI Reconstruction

Value-Informed Skill Chaining for Policy Learning of Long-Horizon Tasks with Surgical Robot

1 code implementation31 Jul 2023 Tao Huang, Kai Chen, Wang Wei, Jianan Li, Yonghao Long, Qi Dou

Based on this value function, a chaining policy is learned to instruct subtask policies to terminate at the state with the highest value so that all subsequent policies are more likely to be connected for accomplishing the task.


LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusion

no code implementations3 Jul 2023 Weiyi Xiong, Jianan Liu, Tao Huang, Qing-Long Han, Yuxuan Xia, Bing Zhu

They are sent to the core of LXL, called "radar occupancy-assisted depth-based sampling", to aid image view transformation.

3D Object Detection Autonomous Driving +3

Positive Label Is All You Need for Multi-Label Classification

no code implementations28 Jun 2023 Zhixiang Yuan, Kaixin Zhang, Tao Huang

Multi-label classification (MLC) suffers from the inevitable label noise in training data due to the difficulty in annotating various semantic labels in each image.

Multi-Label Classification

A step towards digital operations -- A novel grey-box approach for modelling the heat dynamics of Ultra-low temperature freezing chambers

no code implementations13 Jun 2023 Tao Huang, Peder Bacher, Jan Kloppenborg Møller, Francesco D'Ettorre, Wiebke Brix Markussen

In addition, the model for local evaporator temperature can effectively adapt to different operational patterns and provide insight into the local cooling supply status.

energy management

Knowledge Diffusion for Distillation

1 code implementation NeurIPS 2023 Tao Huang, Yuan Zhang, Mingkai Zheng, Shan You, Fei Wang, Chen Qian, Chang Xu

To address this, we propose to denoise student features using a diffusion model trained by teacher features.

Denoising Image Classification +4

Avatar Knowledge Distillation: Self-ensemble Teacher Paradigm with Uncertainty

1 code implementation4 May 2023 Yuan Zhang, Weihua Chen, Yichen Lu, Tao Huang, Xiuyu Sun, Jian Cao

Knowledge distillation is an effective paradigm for boosting the performance of pocket-size model, especially when multiple teacher models are available, the student would break the upper limit again.

Knowledge Distillation object-detection +3

UNAEN: Unsupervised Abnormality Extraction Network for MRI Motion Artifact Reduction

no code implementations4 Jan 2023 Yusheng Zhou, Hao Li, Jianan Liu, Zhengmin Kong, Tao Huang, Euijoon Ahn, Zhihan Lv, Jinman Kim, David Dagan Feng

Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies.

Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention

1 code implementation ICCV 2023 Yunlong Liu, Tao Huang, Weisheng Dong, Fangfang Wu, Xin Li, Guangming Shi

Deep learning-based LLIE methods focus on learning a mapping function between low-light images and normal-light images that outperforms conventional LLIE methods.

Low-Light Image Enhancement Quantization

Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning

1 code implementation1 Jan 2023 Yonghao Long, Wang Wei, Tao Huang, Yuehao Wang, Qi Dou

We showcase the improvement of our simulation environment with the designed new features, and validate effectiveness of incorporating human factors in embodied intelligence through the use of human demonstrations and reinforcement learning as a representative example.

Approximate better, Attack stronger: Adversarial Example Generation via Asymptotically Gaussian Mixture Distribution

no code implementations24 Sep 2022 Zhengwei Fang, Rui Wang, Tao Huang, Liping Jing

In this paper, we propose Multiple Asymptotically Normal Distribution Attacks (MultiANDA), a novel method that explicitly characterizes adversarial perturbations from a learned distribution.

Adversarial Attack

LightViT: Towards Light-Weight Convolution-Free Vision Transformers

1 code implementation12 Jul 2022 Tao Huang, Lang Huang, Shan You, Fei Wang, Chen Qian, Chang Xu

Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias.

Image Classification Inductive Bias +3

GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker without Bells and Whistles

1 code implementation21 Jun 2022 Jianan Liu, Liping Bai, Yuxuan Xia, Tao Huang, Bing Zhu, Qing-Long Han

The global nearest neighbor (GNN) filter, as the earliest random vector-based Bayesian tracking framework, has been adopted in most of state-of-the-arts trackers in the automotive industry.

Autonomous Driving Multi-Object Tracking

Walle: An End-to-End, General-Purpose, and Large-Scale Production System for Device-Cloud Collaborative Machine Learning

no code implementations30 May 2022 Chengfei Lv, Chaoyue Niu, Renjie Gu, Xiaotang Jiang, Zhaode Wang, Bin Liu, Ziqi Wu, Qiulin Yao, Congyu Huang, Panos Huang, Tao Huang, Hui Shu, Jinde Song, Bin Zou, Peng Lan, Guohuan Xu, Fei Wu, Shaojie Tang, Fan Wu, Guihai Chen

Walle consists of a deployment platform, distributing ML tasks to billion-scale devices in time; a data pipeline, efficiently preparing task input; and a compute container, providing a cross-platform and high-performance execution environment, while facilitating daily task iteration.

Masked Distillation with Receptive Tokens

1 code implementation29 May 2022 Tao Huang, Yuan Zhang, Shan You, Fei Wang, Chen Qian, Jian Cao, Chang Xu

To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks.

object-detection Object Detection +1

Knowledge Distillation from A Stronger Teacher

1 code implementation21 May 2022 Tao Huang, Shan You, Fei Wang, Chen Qian, Chang Xu

In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly.

Ranked #2 on Knowledge Distillation on ImageNet (using extra training data)

Image Classification Knowledge Distillation +2

Unsupervised Representation Learning for 3D MRI Super Resolution with Degradation Adaptation

no code implementations13 May 2022 Jianan Liu, Hao Li, Tao Huang, Euijoon Ahn, Kang Han, Adeel Razi, Wei Xiang, Jinman Kim, David Dagan Feng

However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.

Image Registration Representation Learning +1

DyRep: Bootstrapping Training with Dynamic Re-parameterization

2 code implementations CVPR 2022 Tao Huang, Shan You, Bohan Zhang, Yuxuan Du, Fei Wang, Chen Qian, Chang Xu

Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks.

Relational Surrogate Loss Learning

1 code implementation ICLR 2022 Tao Huang, Zekang Li, Hua Lu, Yong Shan, Shusheng Yang, Yang Feng, Fei Wang, Shan You, Chang Xu

Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e. g., average precision and F1 score.

Image Classification Machine Reading Comprehension +2

Accelerating Representation Learning with View-Consistent Dynamics in Data-Efficient Reinforcement Learning

no code implementations18 Jan 2022 Tao Huang, Jiachen Wang, Xiao Chen

Learning informative representations from image-based observations is of fundamental concern in deep Reinforcement Learning (RL).

Data Augmentation reinforcement-learning +2

GreedyNASv2: Greedier Search with a Greedy Path Filter

no code implementations CVPR 2022 Tao Huang, Shan You, Fei Wang, Chen Qian, ChangShui Zhang, Xiaogang Wang, Chang Xu

In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently.

Deep Instance Segmentation with Automotive Radar Detection Points

no code implementations5 Oct 2021 Jianan Liu, Weiyi Xiong, Liping Bai, Yuxuan Xia, Tao Huang, Wanli Ouyang, Bing Zhu

Automotive radar provides reliable environmental perception in all-weather conditions with affordable cost, but it hardly supplies semantic and geometry information due to the sparsity of radar detection points.

Autonomous Driving Clustering +2

Reinforcement Learning with Predictive Consistent Representations

no code implementations29 Sep 2021 Tao Huang, Xiao Chen, Jiachen Wang

Learning informative representations from image-based observations is a fundamental problem in deep Reinforcement Learning (RL).

reinforcement-learning Reinforcement Learning (RL)

Gradient Boosted Binary Histogram Ensemble for Large-scale Regression

no code implementations3 Jun 2021 Hanyuan Hang, Tao Huang, Yuchao Cai, Hanfang Yang, Zhouchen Lin

In this paper, we propose a gradient boosting algorithm for large-scale regression problems called \textit{Gradient Boosted Binary Histogram Ensemble} (GBBHE) based on binary histogram partition and ensemble learning.

Ensemble Learning regression

Prioritized Architecture Sampling with Monto-Carlo Tree Search

1 code implementation CVPR 2021 Xiu Su, Tao Huang, Yanxi Li, Shan You, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu

One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once.

Neural Architecture Search

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging

1 code implementation CVPR 2021 Tao Huang, Weisheng Dong, Xin Yuan, Jinjian Wu, Guangming Shi

Different from existing GSM models using hand-crafted scale priors (e. g., the Jeffrey's prior), we propose to learn the scale prior through a deep convolutional neural network (DCNN).

Locally Free Weight Sharing for Network Width Search

no code implementations ICLR 2021 Xiu Su, Shan You, Tao Huang, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu

In this paper, to better evaluate each width, we propose a locally free weight sharing strategy (CafeNet) accordingly.

Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images

11 code implementations CVPR 2021 Tao Huang, Songjiang Li, Xu Jia, Huchuan Lu, Jianzhuang Liu

In this paper, we present a very simple yet effective method named Neighbor2Neighbor to train an effective image denoising model with only noisy images.

Image Denoising Self-Supervised Learning

Explicit Learning Topology for Differentiable Neural Architecture Search

no code implementations1 Jan 2021 Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang

Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types.

Neural Architecture Search

Wasserstein Distributionally Robust Optimization: A Three-Player Game Framework

no code implementations1 Jan 2021 Zhuozhuo Tu, Shan You, Tao Huang, DaCheng Tao

Wasserstein distributionally robust optimization (DRO) has recently received significant attention in machine learning due to its connection to generalization, robustness and regularization.

Stretchable Cells Help DARTS Search Better

no code implementations18 Nov 2020 Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang

However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells.

Neural Architecture Search

MG-GCN: Fast and Effective Learning with Mix-grained Aggregators for Training Large Graph Convolutional Networks

no code implementations17 Nov 2020 Tao Huang, Yihan Zhang, Jiajing Wu, Junyuan Fang, Zibin Zheng

To tackle the dilemma between accuracy and efficiency, we propose to use aggregators with different granularities to gather neighborhood information in different layers.

Data Agnostic Filter Gating for Efficient Deep Networks

no code implementations28 Oct 2020 Xiu Su, Shan You, Tao Huang, Hongyan Xu, Fei Wang, Chen Qian, ChangShui Zhang, Chang Xu

To deploy a well-trained CNN model on low-end computation edge devices, it is usually supposed to compress or prune the model under certain computation budget (e. g., FLOPs).

Quantum circuit architecture search for variational quantum algorithms

1 code implementation20 Oct 2020 Yuxuan Du, Tao Huang, Shan You, Min-Hsiu Hsieh, DaCheng Tao

Variational quantum algorithms (VQAs) are expected to be a path to quantum advantages on noisy intermediate-scale quantum devices.

MMD GAN with Random-Forest Kernels

no code implementations ICLR 2020 Tao Huang, Zhen Han, Xu Jia, Hanyuan Hang

In this paper, we propose a novel kind of kernel, random forest kernel, to enhance the empirical performance of MMD GAN.

Ensemble Learning

Robust Data Preprocessing for Machine-Learning-Based Disk Failure Prediction in Cloud Production Environments

no code implementations20 Dec 2019 Shujie Han, Jun Wu, Erci Xu, Cheng He, Patrick P. C. Lee, Yi Qiang, Qixing Zheng, Tao Huang, Zixi Huang, Rui Li

To provide proactive fault tolerance for modern cloud data centers, extensive studies have proposed machine learning (ML) approaches to predict imminent disk failures for early remedy and evaluated their approaches directly on public datasets (e. g., Backblaze SMART logs).

BIG-bench Machine Learning

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