Search Results for author: Huafeng Liu

Found 24 papers, 6 papers with code

Unsupervised Learning of Hybrid Latent Dynamics: A Learn-to-Identify Framework

no code implementations13 Mar 2024 Yubo Ye, Sumeet Vadhavkar, Xiajun Jiang, Ryan Missel, Huafeng Liu, Linwei Wang

Modern applications increasingly require unsupervised learning of latent dynamics from high-dimensional time-series.

Inductive Bias Meta-Learning +1

Hybrid Kinetics Embedding Framework for Dynamic PET Reconstruction

no code implementations12 Mar 2024 Yubo Ye, Huafeng Liu, Linwei Wang

We then embed this hybrid model at the latent space of an encoding-decoding framework to enable both supervised and unsupervised identification of the hybrid kinetics and thereby dynamic PET reconstruction.

VideoMAC: Video Masked Autoencoders Meet ConvNets

1 code implementation29 Feb 2024 Gensheng Pei, Tao Chen, Xiruo Jiang, Huafeng Liu, Zeren Sun, Yazhou Yao

In this paper, we propose a new approach termed as \textbf{VideoMAC}, which combines video masked autoencoders with resource-friendly ConvNets.

Pose Tracking Representation Learning +4

Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection

no code implementations17 Feb 2024 Huafeng Liu, Mengmeng Sheng, Zeren Sun, Yazhou Yao, Xian-Sheng Hua, Heng-Tao Shen

Specifically, we propose Class-Balance-based sample Selection (CBS) to prevent the tail class samples from being neglected during training.

Learning with noisy labels

Glioblastoma Tumor Segmentation using an Ensemble of Vision Transformers

no code implementations9 Nov 2023 Huafeng Liu, Benjamin Dowdell, Todd Engelder, Zarah Pulmano, Nicolas Osa, Arko Barman

Analysis of Magnetic Resonance Imaging (MRI) scans is one of the most effective methods for the diagnosis and treatment of brain cancers such as glioblastoma.

Tumor Segmentation

STPDnet: Spatial-temporal convolutional primal dual network for dynamic PET image reconstruction

no code implementations8 Mar 2023 Rui Hu, Jianan Cui, Chengjin Yu, YunMei Chen, Huafeng Liu

Dynamic positron emission tomography (dPET) image reconstruction is extremely challenging due to the limited counts received in individual frame.

Image Reconstruction

LMPDNet: TOF-PET list-mode image reconstruction using model-based deep learning method

no code implementations21 Feb 2023 Chenxu Li, Rui Hu, Jianan Cui, Huafeng Liu

Additionally, we compare the spatial and temporal consumption of list-mode data and sinogram data in model-based deep learning methods, demonstrating the superiority of list-mode data in model-based TOF-PET reconstruction.

Image Reconstruction

FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network

1 code implementation19 Jan 2023 Huafeng Liu, Pai Peng, Tao Chen, Qiong Wang, Yazhou Yao, Xian-Sheng Hua

Few-shot semantic segmentation is the task of learning to locate each pixel of the novel class in the query image with only a few annotated support images.

Few-Shot Semantic Segmentation

Learning Intrinsic and Extrinsic Intentions for Cold-start Recommendation with Neural Stochastic Processes

no code implementations MM '22: Proceedings of the 30th ACM International Conference on Multimedia 2022 Huafeng Liu, Liping Jing, Dahai Yu, Mingjie Zhou, Michael Ng

In this paper, we propose an intention neural process model (INP) for user cold-start recommendation (i. e., user with very few historical interactions), a novel extension of the neural stochastic process family using a general meta learning strategy with intrinsic and extrinsic intention learning for robust user preference learning.

Decision Making Meta-Learning

Deep Amortized Relational Model with Group-Wise Hierarchical Generative Process

no code implementations AAAI 2022 Huafeng Liu, Tong Zhou, Jiaqi Wang, Liping Jing

In this paper, we propose Deep amortized Relational Model (DaRM) with group-wise hierarchical generative process for community discovery and link prediction on relational data (e. g., graph, network).

Community Detection Link Prediction

HessianFR: An Efficient Hessian-based Follow-the-Ridge Algorithm for Minimax Optimization

no code implementations23 May 2022 Yihang Gao, Huafeng Liu, Michael K. Ng, Mingjie Zhou

Wide applications of differentiable two-player sequential games (e. g., image generation by GANs) have raised much interest and attention of researchers to study efficient and fast algorithms.

Image Generation

TransEM:Residual Swin-Transformer based regularized PET image reconstruction

no code implementations9 May 2022 Rui Hu, Huafeng Liu

Positron emission tomography(PET) image reconstruction is an ill-posed inverse problem and suffers from high level of noise due to limited counts received.

Image Reconstruction

Cluster-Wise Hierarchical Generative Model for Deep Amortized Clustering

no code implementations CVPR 2021 Huafeng Liu, Jiaqi Wang, Liping Jing

In this paper, we propose Cluster-wise Hierarchical Generative Model for deep amortized clustering (CHiGac).


Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones

1 code implementation23 Jan 2021 Huafeng Liu, Chuanyi Zhang, Yazhou Yao, Xiushen Wei, Fumin Shen, Jian Zhang, Zhenmin Tang

Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators.

Fine-Grained Visual Recognition

Interpretable Image Recognition by Constructing Transparent Embedding Space

2 code implementations ICCV 2021 Jiaqi Wang, Huafeng Liu, Xinyue Wang, Liping Jing

This plug-in embedding space is spanned by transparent basis concepts which are constructed on the Grassmann manifold.

Super Resolution of Arterial Spin Labeling MR Imaging Using Unsupervised Multi-Scale Generative Adversarial Network

no code implementations14 Sep 2020 Jianan Cui, Kuang Gong, Paul Han, Huafeng Liu, Quanzheng Li

After the network was trained, the super-resolution (SR) image was generated by supplying the upsampled LR ASL image and corresponding T1-weighted image to the generator of the last layer.

Generative Adversarial Network SSIM +1

Clinically Translatable Direct Patlak Reconstruction from Dynamic PET with Motion Correction Using Convolutional Neural Network

no code implementations13 Sep 2020 Nuobei Xie, Kuang Gong, Ning Guo, Zhixing Qin, Jianan Cui, Zhifang Wu, Huafeng Liu, Quanzheng Li

Patlak model is widely used in 18F-FDG dynamic positron emission tomography (PET) imaging, where the estimated parametric images reveal important biochemical and physiology information.


Deep Representation Learning for Road Detection through Siamese Network

no code implementations26 May 2019 Huafeng Liu, Xiaofeng Han, Xiangrui Li, Yazhou Yao, Pu Huang, Zhenming Tang

We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network.

Autonomous Driving Representation Learning

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