Search Results for author: Hao Zheng

Found 39 papers, 12 papers with code

SurfNN: Joint Reconstruction of Multiple Cortical Surfaces from Magnetic Resonance Images

no code implementations6 Mar 2023 Hao Zheng, Hongming Li, Yong Fan

Different from existing deep learning-based cortical surface reconstruction methods that either reconstruct the cortical surfaces separately or neglect the interdependence between the inner and outer surfaces, SurfNN reconstructs both the inner and outer cortical surfaces jointly by training a single network to predict a midthickness surface that lies at the center of the inner and outer cortical surfaces.

Surface Reconstruction

Deep Clustering Survival Machines with Interpretable Expert Distributions

no code implementations27 Jan 2023 BoJian Hou, Hongming Li, Zhicheng Jiao, Zhen Zhou, Hao Zheng, Yong Fan

We learn weights of the expert distributions for individual instances according to their features discriminatively such that each instance's survival information can be characterized by a weighted combination of the learned constant expert distributions.

Deep Clustering Survival Analysis

Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning

no code implementations12 Dec 2022 Hao Zheng, Mirella Lapata

Compositional generalization is a basic mechanism in human language learning, which current neural networks struggle with.

Machine Translation

A Point in the Right Direction: Vector Prediction for Spatially-aware Self-supervised Volumetric Representation Learning

no code implementations15 Nov 2022 Yejia Zhang, Pengfei Gu, Nishchal Sapkota, Hao Zheng, Peixian Liang, Danny Z. Chen

High annotation costs and limited labels for dense 3D medical imaging tasks have recently motivated an assortment of 3D self-supervised pretraining methods that improve transfer learning performance.

Image Segmentation Medical Image Segmentation +3

Dance of SNN and ANN: Solving binding problem by combining spike timing and reconstructive attention

1 code implementation11 Nov 2022 Hao Zheng, Hui Lin, Rong Zhao, Luping Shi

In this paper, we propose a brain-inspired hybrid neural network (HNN) that introduces temporal binding theory originated from neuroscience into ANNs by integrating spike timing dynamics (via spiking neural networks, SNNs) with reconstructive attention (by ANNs).

Mining SoC Message Flows with Attention Model

no code implementations12 Sep 2022 Md Rubel Ahmed, Bardia Nadimi, Hao Zheng

High-quality system-level message flow specifications are necessary for comprehensive validation of system-on-chip (SoC) designs.

Usable Region Estimate for Assessing Practical Usability of Medical Image Segmentation Models

1 code implementation1 Jul 2022 Yizhe Zhang, Suraj Mishra, Peixian Liang, Hao Zheng, Danny Z. Chen

We aim to quantitatively measure the practical usability of medical image segmentation models: to what extent, how often, and on which samples a model's predictions can be used/trusted.

Image Segmentation Medical Image Segmentation +1

Deep Bidirectional Transformers for SoC Flow Specification Mining

no code implementations9 Mar 2022 Md Rubel Ahmed, Hao Zheng

High-quality system-level message flow specifications can lead to comprehensive validation of system-on-chip (SoC) designs.

LTSP: Long-Term Slice Propagation for Accurate Airway Segmentation

no code implementations13 Feb 2022 Yangqian Wu, Minghui Zhang, Weihao Yu, Hao Zheng, Jiasheng Xu, Yun Gu

Methods: In this paper, a long-term slice propagation (LTSP) method is proposed for accurate airway segmentation from pathological CT scans.

Computed Tomography (CT)

BREAK: Bronchi Reconstruction by gEodesic transformation And sKeleton embedding

no code implementations29 Jan 2022 Weihao Yu, Hao Zheng, Minghui Zhang, Hanxiao Zhang, Jiayuan Sun, Jie Yang

Since the volume of the peripheral bronchi may be much smaller than the large branches in an input patch, the common segmentation loss is not sensitive to the breakages among the distal branches.

Disentangled Sequence to Sequence Learning for Compositional Generalization

1 code implementation ACL 2022 Hao Zheng, Mirella Lapata

There is mounting evidence that existing neural network models, in particular the very popular sequence-to-sequence architecture, struggle to systematically generalize to unseen compositions of seen components.

Disentanglement Machine Translation +2

FDA: Feature Decomposition and Aggregation for Robust Airway Segmentation

no code implementations7 Sep 2021 Minghui Zhang, Xin Yu, Hanxiao Zhang, Hao Zheng, Weihao Yu, Hong Pan, Xiangran Cai, Yun Gu

Compared to other state-of-the-art transfer learning methods, our method accurately segmented more bronchi in the noisy CT scans.

Transfer Learning

Hierarchical Self-Supervised Learning for Medical Image Segmentation Based on Multi-Domain Data Aggregation

no code implementations10 Jul 2021 Hao Zheng, Jun Han, Hongxiao Wang, Lin Yang, Zhuo Zhao, Chaoli Wang, Danny Z. Chen

Unlike the current literature on task-specific self-supervised pretraining followed by supervised fine-tuning, we utilize SSL to learn task-agnostic knowledge from heterogeneous data for various medical image segmentation tasks.

Image Segmentation Medical Image Segmentation +3

Model Synthesis for Communication Traces of System-on-Chip Designs

no code implementations13 Feb 2021 Hao Zheng, Md Rubel Ahmed, Parijat Mukherjee, Mahesh C. Ketkar, Jin Yang

In this paper, we consider the problem of inferring models from communication traces of system-on-chip~(SoC) designs.

Categorical computation

no code implementations9 Feb 2021 Liang Kong, Hao Zheng

We provide a theoretical idea of realizing (higher) functors physically based on the physics of topological orders.

Quantum Physics Strongly Correlated Electrons Category Theory

Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation

no code implementations17 Dec 2020 Hongxiao Wang, Hao Zheng, Jianxu Chen, Lin Yang, Yizhe Zhang, Danny Z. Chen

Second, we devise an effective data selection policy for judiciously sampling the generated images: (1) to make the generated training set better cover the dataset, the clusters that are underrepresented in the original training set are covered more; (2) to make the training process more effective, we identify and oversample the images of "hard cases" in the data for which annotated training data may be scarce.

Image Generation Image Segmentation +1

Learning Tubule-Sensitive CNNs for Pulmonary Airway and Artery-Vein Segmentation in CT

no code implementations10 Dec 2020 Yulei Qin, Hao Zheng, Yun Gu, Xiaolin Huang, Jie Yang, Lihui Wang, Feng Yao, Yue-Min Zhu, Guang-Zhong Yang

Training convolutional neural networks (CNNs) for segmentation of pulmonary airway, artery, and vein is challenging due to sparse supervisory signals caused by the severe class imbalance between tubular targets and background.

Anatomy Representation Learning

Alleviating Class-wise Gradient Imbalance for Pulmonary Airway Segmentation

1 code implementation24 Nov 2020 Hao Zheng, Yulei Qin, Yun Gu, Fangfang Xie, Jie Yang, Jiayuan Sun, Guang-Zhong Yang

Due to the small size and scattered spatial distribution of peripheral bronchi, this is hampered by severe class imbalance between foreground and background regions, which makes it challenging for CNN-based methods to parse distal small airways.

Action Segmentation

Compositional Generalization via Semantic Tagging

no code implementations Findings (EMNLP) 2021 Hao Zheng, Mirella Lapata

Although neural sequence-to-sequence models have been successfully applied to semantic parsing, they fail at compositional generalization, i. e., they are unable to systematically generalize to unseen compositions of seen components.

Semantic Parsing TAG

Diagnosis of electron density and temperature by using collisional radiative model in capacitively coupled Ar plasmas II: two-dimensional distributions

no code implementations21 Oct 2020 Jidun Wu, Hao Zheng, Yanfei Wang, Fengzhu Zhou, Xiaojiang Huang

Effects of radio-frequency power and driven frequency on the two-dimensional (axial and radial) distributions of electron density and temperature were experimentally investigated in low pressure capacitively coupled argon plasmas.

Plasma Physics

Diagnosis of electron density and temperature by using collisional radiative model in capacitively coupled Ar plasmas I: triple-frequency discharges

no code implementations21 Oct 2020 Hao Zheng, Jidun Wu, Qilu Cao, Jiaojiao Zhang, Xiaojiang Huang

Compared with the dual-frequency (DF) CCPs, it is found that with the increase of IF power, the HF power can control the electron density more independently with less influence on the electron temperature.

Plasma Physics

Brain-inspired global-local learning incorporated with neuromorphic computing

no code implementations5 Jun 2020 Yujie Wu, Rong Zhao, Jun Zhu, Feng Chen, Mingkun Xu, Guoqi Li, Sen Song, Lei Deng, Guanrui Wang, Hao Zheng, Jing Pei, Youhui Zhang, Mingguo Zhao, Luping Shi

We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors.

Continual Learning Few-Shot Learning

Mining Message Flows using Recurrent Neural Networks for System-on-Chip Designs

no code implementations29 Apr 2020 Yuting Cao, Parijat Mukherjee, Mahesh Ketkar, Jin Yang, Hao Zheng

Initial results show that the proposed approach is capable of extracting various patterns on system-level specifications from the highly concurrent SoC execution traces.

Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction

1 code implementation NeurIPS 2019 Hao Zheng, Faming Fang, Guixu Zhang

Compressed Sensing MRI (CS-MRI) aims at reconstrcuting de-aliased images from sub-Nyquist sampling k-space data to accelerate MR Imaging.

MRI Reconstruction

Sentence Centrality Revisited for Unsupervised Summarization

1 code implementation ACL 2019 Hao Zheng, Mirella Lapata

Single document summarization has enjoyed renewed interests in recent years thanks to the popularity of neural network models and the availability of large-scale datasets.

Document Summarization News Summarization +2

SPDA: Superpixel-based Data Augmentation for Biomedical Image Segmentation

no code implementations28 Feb 2019 Yizhe Zhang, Lin Yang, Hao Zheng, Peixian Liang, Colleen Mangold, Raquel G. Loreto, David. P. Hughes, Danny Z. Chen

To better mimic human visual perception, we think it is desirable for the deep learning model to be able to perceive not only raw images but also SP images.

Data Augmentation Image Segmentation +1

Cascade Decoder: A Universal Decoding Method for Biomedical Image Segmentation

no code implementations15 Jan 2019 Peixian Liang, Jianxu Chen, Hao Zheng, Lin Yang, Yizhe Zhang, Danny Z. Chen

The cascade decoder structure aims to conduct more effective decoding of hierarchically encoded features and is more compatible with common encoders than the known decoders.

Image Segmentation Semantic Segmentation

A New Ensemble Learning Framework for 3D Biomedical Image Segmentation

1 code implementation10 Dec 2018 Hao Zheng, Yizhe Zhang, Lin Yang, Peixian Liang, Zhuo Zhao, Chaoli Wang, Danny Z. Chen

In this paper, we propose a new ensemble learning framework for 3D biomedical image segmentation that combines the merits of 2D and 3D models.

3D Medical Imaging Segmentation Ensemble Learning +2

Varifocal-Net: A Chromosome Classification Approach using Deep Convolutional Networks

1 code implementation13 Oct 2018 Yulei Qin, Juan Wen, Hao Zheng, Xiaolin Huang, Jie Yang, Ning Song, Yue-Min Zhu, Lingqian Wu, Guang-Zhong Yang

To expedite the diagnosis, we present a novel method named Varifocal-Net for simultaneous classification of chromosome's type and polarity using deep convolutional networks.

Classification General Classification +2

Deep Learning Based Instance Segmentation in 3D Biomedical Images Using Weak Annotation

no code implementations28 Jun 2018 Zhuo Zhao, Lin Yang, Hao Zheng, Ian H. Guldner, Si-Yuan Zhang, Danny Z. Chen

Our approach needs only 3D bounding boxes for all instances and full voxel annotation for a small fraction of the instances, and uses a novel two-stage 3D instance segmentation model utilizing these two kinds of annotation, respectively.

3D Instance Segmentation Semantic Segmentation

MLE-induced Likelihood for Markov Random Fields

no code implementations27 Mar 2018 Jie Liu, Hao Zheng

Especially as the size of the MRF increases, both the numerical performance and the computational cost of our approach remain consistently satisfactory, whereas Laplace approximation deteriorates and pseudolikelihood becomes computationally unbearable.

On the Hecke algebras and the colored HOMFLY polynomial

1 code implementation11 Jan 2006 Xiao-Song Lin, Hao Zheng

The colored HOMFLY polynomial is the quantum invariant of oriented links in $S^3$ associated with irreducible representations of the quantum group $U_q(\mathrm{sl}_N)$.

Quantum Algebra Geometric Topology

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