Search Results for author: Zhepeng Wang

Found 25 papers, 1 papers with code

VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection

no code implementations5 Jan 2024 Ziying Song, Guoxin Zhang, Jun Xie, Lin Liu, Caiyan Jia, Shaoqing Xu, Zhepeng Wang

In particular, we propose a voxel-based image pipeline that involves projecting point clouds onto images to obtain both pixel- and patch-level features.

3D Object Detection Feature Importance +2

Technical Report for Argoverse Challenges on 4D Occupancy Forecasting

no code implementations27 Nov 2023 Pengfei Zheng, Kanokphan Lertniphonphan, Feng Chen, Siwei Chen, Bingchuan Sun, Jun Xie, Zhepeng Wang

This report presents our Le3DE2E_Occ solution for 4D Occupancy Forecasting in Argoverse Challenges at CVPR 2023 Workshop on Autonomous Driving (WAD).

Autonomous Driving

Edge-InversionNet: Enabling Efficient Inference of InversionNet on Edge Devices

no code implementations14 Oct 2023 Zhepeng Wang, Isaacshubhanand Putla, Weiwen Jiang, Youzuo Lin

Seismic full waveform inversion (FWI) is a widely used technique in geophysics for inferring subsurface structures from seismic data.

Geophysics

A Novel Spatial-Temporal Variational Quantum Circuit to Enable Deep Learning on NISQ Devices

no code implementations19 Jul 2023 Jinyang Li, Zhepeng Wang, Zhirui Hu, Prasanna Date, Ang Li, Weiwen Jiang

The results of the evaluation on the standard dataset for binary classification show that ST-VQC can achieve over 30% accuracy improvement compared with existing VQCs on actual quantum computers.

Binary Classification

QuMoS: A Framework for Preserving Security of Quantum Machine Learning Model

no code implementations23 Apr 2023 Zhepeng Wang, Jinyang Li, Zhirui Hu, Blake Gage, Elizabeth Iwasawa, Weiwen Jiang

We further developed a reinforcement learning-based security engine, which can automatically optimize the model design under the distributed setting, such that a good trade-off between model performance and security can be made.

Neural Architecture Search Quantum Machine Learning

Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis

no code implementations24 Aug 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yi Sheng, Lei Yang, Alaina J. James, Yiyu Shi, Jingtong Hu

Self-supervised learning (SSL) methods, contrastive learning (CL) and masked autoencoders (MAE), can leverage the unlabeled data to pre-train models, followed by fine-tuning with limited labels.

Contrastive Learning Federated Learning +1

Distributed Contrastive Learning for Medical Image Segmentation

no code implementations7 Aug 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yiyu Shi, Jingtong Hu

However, when adopting CL in FL, the limited data diversity on each site makes federated contrastive learning (FCL) ineffective.

Contrastive Learning Federated Learning +4

Quantum Neural Network Compression

no code implementations4 Jul 2022 Zhirui Hu, Peiyan Dong, Zhepeng Wang, Youzuo Lin, Yanzhi Wang, Weiwen Jiang

Model compression, such as pruning and quantization, has been widely applied to optimize neural networks on resource-limited classical devices.

Neural Network Compression Quantization

Federated Contrastive Learning for Volumetric Medical Image Segmentation

no code implementations23 Apr 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yiyu Shi, Jingtong Hu

However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective.

Contrastive Learning Federated Learning +4

Synthetic Data Can Also Teach: Synthesizing Effective Data for Unsupervised Visual Representation Learning

no code implementations14 Feb 2022 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

To tackle this problem, we propose a data generation framework with two methods to improve CL training by joint sample generation and contrastive learning.

Contrastive Learning Representation Learning +2

Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning

no code implementations14 Feb 2022 Yawen Wu, Dewen Zeng, Zhepeng Wang, Yi Sheng, Lei Yang, Alaina J. James, Yiyu Shi, Jingtong Hu

The recently developed self-supervised learning approach, contrastive learning (CL), can leverage the unlabeled data to pre-train a model, after which the model is fine-tuned on limited labeled data for dermatological disease diagnosis.

Contrastive Learning Federated Learning +1

Decentralized Unsupervised Learning of Visual Representations

no code implementations21 Nov 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Meng Li, Yiyu Shi, Jingtong Hu

To tackle this problem, we propose a collaborative contrastive learning framework consisting of two approaches: feature fusion and neighborhood matching, by which a unified feature space among clients is learned for better data representations.

Contrastive Learning Federated Learning +2

Data-Efficient Contrastive Learning by Differentiable Hard Sample and Hard Positive Pair Generation

no code implementations29 Sep 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

In this way, the main model learns to cluster hard positives by pulling the representations of similar yet distinct samples together, by which the representations of similar samples are well-clustered and better representations can be learned.

Contrastive Learning Self-Supervised Learning

Federated Contrastive Representation Learning with Feature Fusion and Neighborhood Matching

no code implementations29 Sep 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Meng Li, Yiyu Shi, Jingtong Hu

Federated learning (FL) enables distributed clients to learn a shared model for prediction while keeping the training data local on each client.

Contrastive Learning Federated Learning +2

Exploration of Quantum Neural Architecture by Mixing Quantum Neuron Designs

no code implementations8 Sep 2021 Zhepeng Wang, Zhiding Liang, Shanglin Zhou, Caiwen Ding, Yiyu Shi, Weiwen Jiang

Experimental results demonstrate that the identified quantum neural architectures with mixed quantum neurons can achieve 90. 62% of accuracy on the MNIST dataset, compared with 52. 77% and 69. 92% on the VQC and QuantumFlow, respectively.

Can Noise on Qubits Be Learned in Quantum Neural Network? A Case Study on QuantumFlow

no code implementations8 Sep 2021 Zhiding Liang, Zhepeng Wang, Junhuan Yang, Lei Yang, JinJun Xiong, Yiyu Shi, Weiwen Jiang

Specifically, this paper targets quantum neural network (QNN), and proposes to learn the errors in the training phase, so that the identified QNN model can be resilient to noise.

Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast

no code implementations7 Jun 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

After a model is deployed on edge devices, it is desirable for these devices to learn from unlabeled data to continuously improve accuracy.

Contrastive Learning

Enabling Efficient On-Device Self-supervised Contrastive Learning by Data Selection

no code implementations1 Jan 2021 Yawen Wu, Zhepeng Wang, Dewen Zeng, Yiyu Shi, Jingtong Hu

In this paper, we propose a framework to automatically select the most representative data from unlabeled input stream on-the-fly, which only requires the use of a small data buffer for dynamic learning.

Contrastive Learning

Personalized Deep Learning for Ventricular Arrhythmias Detection on Medical IoT Systems

no code implementations18 Aug 2020 Zhenge Jia, Zhepeng Wang, Feng Hong, Lichuan Ping, Yiyu Shi, Jingtong Hu

We equip the system with real-time inference on both intracardiac and surface rhythm monitors.

Enabling On-Device CNN Training by Self-Supervised Instance Filtering and Error Map Pruning

no code implementations7 Jul 2020 Yawen Wu, Zhepeng Wang, Yiyu Shi, Jingtong Hu

For example, when training ResNet-110 on CIFAR-10, we achieve 68% computation saving while preserving full accuracy and 75% computation saving with a marginal accuracy loss of 1. 3%.

Quantization

Intermittent Inference with Nonuniformly Compressed Multi-Exit Neural Network for Energy Harvesting Powered Devices

no code implementations23 Apr 2020 Yawen Wu, Zhepeng Wang, Zhenge Jia, Yiyu Shi, Jingtong Hu

This work aims to enable persistent, event-driven sensing and decision capabilities for energy-harvesting (EH)-powered devices by deploying lightweight DNNs onto EH-powered devices.

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