Search Results for author: Jianfeng Feng

Found 39 papers, 17 papers with code

fMRI-3D: A Comprehensive Dataset for Enhancing fMRI-based 3D Reconstruction

no code implementations17 Sep 2024 Jianxiong Gao, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng, Yanwei Fu

To advance this task, we present the fMRI-3D dataset, which includes data from 15 participants and showcases a total of 4768 3D objects.

3D Reconstruction

Towards free-response paradigm: a theory on decision-making in spiking neural networks

no code implementations16 Apr 2024 Zhichao Zhu, Yang Qi, Wenlian Lu, Zhigang Wang, Lu Cao, Jianfeng Feng

The energy-efficient and brain-like information processing abilities of Spiking Neural Networks (SNNs) have attracted considerable attention, establishing them as a crucial element of brain-inspired computing.

Decision Making

NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation

no code implementations27 Mar 2024 Jingyang Huo, Yikai Wang, Xuelin Qian, Yun Wang, Chong Li, Jianfeng Feng, Yanwei Fu

Recent fMRI-to-image approaches mainly focused on associating fMRI signals with specific conditions of pre-trained diffusion models.

Image Reconstruction

OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation

no code implementations18 Mar 2024 Haochen Jiang, Yueming Xu, Yihan Zeng, Hang Xu, Wei zhang, Jianfeng Feng, Li Zhang

We model the geometric structure of the scene with occupancy representation and distill the pre-trained open vocabulary model into a 3D language field via volume rendering for zero-shot inference.

3D Reconstruction 3D Scene Reconstruction +3

Efficient Combinatorial Optimization via Heat Diffusion

1 code implementation13 Mar 2024 Hengyuan Ma, Wenlian Lu, Jianfeng Feng

Combinatorial optimization problems are widespread but inherently challenging due to their discrete nature.

Combinatorial Optimization

Bayesian Unsupervised Disentanglement of Anatomy and Geometry for Deep Groupwise Image Registration

no code implementations4 Jan 2024 Xinzhe Luo, Xin Wang, Linda Shapiro, Chun Yuan, Jianfeng Feng, Xiahai Zhuang

We propose a novel hierarchical variational auto-encoding architecture to realise the inference procedure of the latent variables, where the registration parameters can be explicitly estimated in a mathematically interpretable fashion.

Anatomy Bayesian Inference +2

Learn to integrate parts for whole through correlated neural variability

1 code implementation1 Jan 2024 Zhichao Zhu, Yang Qi, Wenlian Lu, Jianfeng Feng

Sensory perception originates from the responses of sensory neurons, which react to a collection of sensory signals linked to various physical attributes of a singular perceptual object.

MinD-3D: Reconstruct High-quality 3D objects in Human Brain

no code implementations12 Dec 2023 Jianxiong Gao, Yuqian Fu, Yun Wang, Xuelin Qian, Jianfeng Feng, Yanwei Fu

In this paper, we introduce Recon3DMind, an innovative task aimed at reconstructing 3D visuals from Functional Magnetic Resonance Imaging (fMRI) signals, marking a significant advancement in the fields of cognitive neuroscience and computer vision.

Brain Decoding Decoder +1

HiFi-Syn: Hierarchical Granularity Discrimination for High-Fidelity Synthesis of MR Images with Structure Preservation

no code implementations21 Nov 2023 Ziqi Yu, Botao Zhao, Shengjie Zhang, Xiang Chen, Jianfeng Feng, Tingying Peng, Xiao-Yong Zhang

To address these issues, we introduce hierarchical granularity discrimination, which exploits various levels of semantic information present in medical images.

Translation

fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding

no code implementations1 Nov 2023 Xuelin Qian, Yun Wang, Jingyang Huo, Jianfeng Feng, Yanwei Fu

The exploration of brain activity and its decoding from fMRI data has been a longstanding pursuit, driven by its potential applications in brain-computer interfaces, medical diagnostics, and virtual reality.

Digital Twin Brain: a simulation and assimilation platform for whole human brain

no code implementations2 Aug 2023 Wenlian Lu, Longbin Zeng, Xin Du, Wenyong Zhang, Shitong Xiang, Huarui Wang, Jiexiang Wang, Mingda Ji, Yubo Hou, Minglong Wang, Yuhao Liu, Zhongyu Chen, Qibao Zheng, Ningsheng Xu, Jianfeng Feng

In comparison to most brain simulations with a homogeneous global structure, we highlight that the sparseness, couplingness and heterogeneity in the sMRI, DTI and PET data of the brain has an essential impact on the efficiency of brain simulation, which is proved from the scaling experiments that the DTB of human brain simulation is communication-intensive and memory-access intensive computing systems rather than computation-intensive.

Probabilistic computation and uncertainty quantification with emerging covariance

1 code implementation30 May 2023 Hengyuan Ma, Yang Qi, Li Zhang, Wenlian Lu, Jianfeng Feng

Building robust, interpretable, and secure AI system requires quantifying and representing uncertainty under a probabilistic perspective to mimic human cognitive abilities.

Uncertainty Quantification

Toward stochastic neural computing

2 code implementations23 May 2023 Yang Qi, Zhichao Zhu, Yiming Wei, Lu Cao, Zhigang Wang, Jie Zhang, Wenlian Lu, Jianfeng Feng

To account for the propagation of correlated neural variability, we derive from first principles a moment embedding for spiking neural network (SNN).

Joint fMRI Decoding and Encoding with Latent Embedding Alignment

no code implementations26 Mar 2023 Xuelin Qian, Yikai Wang, Yanwei Fu, Xinwei Sun, xiangyang xue, Jianfeng Feng

Our Latent Embedding Alignment (LEA) model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.

Image Generation

Preconditioned Score-based Generative Models

1 code implementation13 Feb 2023 Hengyuan Ma, Li Zhang, Xiatian Zhu, Jianfeng Feng

Compared with the latest generative models (\eg, CLD-SGM, DDIM, and Analytic-DDIM), PDS can achieve the best sampling quality on CIFAR-10 at a FID score of 1. 99.

Image Generation

Rethinking Precision of Pseudo Label: Test-Time Adaptation via Complementary Learning

no code implementations15 Jan 2023 Jiayi Han, Longbin Zeng, Liang Du, Weiyang Ding, Jianfeng Feng

In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions.

Pseudo Label Test-time Adaptation

MouseGAN++: Unsupervised Disentanglement and Contrastive Representation for Multiple MRI Modalities Synthesis and Structural Segmentation of Mouse Brain

no code implementations4 Dec 2022 Ziqi Yu, Xiaoyang Han, Shengjie Zhang, Jianfeng Feng, Tingying Peng, Xiao-Yong Zhang

Our results demonstrate that MouseGAN++, as a simultaneous image synthesis and segmentation method, can be used to fuse cross-modality information in an unpaired manner and yield more robust performance in the absence of multimodal data.

Disentanglement Image Generation +1

Simulation and assimilation of the digital human brain

no code implementations29 Nov 2022 Wenlian Lu, Xin Du, Jiexiang Wang, Longbin Zeng, Leijun Ye, Shitong Xiang, Qibao Zheng, Jie Zhang, Ningsheng Xu, Jianfeng Feng

Here, we present the Digital Brain (DB), a platform for simulating spiking neuronal networks at the large neuron scale of the human brain based on personalized magnetic-resonance-imaging data and biological constraints.

Vision Transformers: From Semantic Segmentation to Dense Prediction

3 code implementations19 Jul 2022 Li Zhang, Jiachen Lu, Sixiao Zheng, Xinxuan Zhao, Xiatian Zhu, Yanwei Fu, Tao Xiang, Jianfeng Feng, Philip H. S. Torr

Extensive experiments show that our methods achieve appealing performance on a variety of dense prediction tasks (e. g., object detection and instance segmentation and semantic segmentation) as well as image classification.

Image Classification Instance Segmentation +5

Softmax-free Linear Transformers

1 code implementation5 Jul 2022 Jiachen Lu, Junge Zhang, Xiatian Zhu, Jianfeng Feng, Tao Xiang, Li Zhang

With linear complexity, much longer token sequences are permitted by SOFT, resulting in superior trade-off between accuracy and complexity.

Computational Efficiency

Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

1 code implementation5 Jul 2022 Hengyuan Ma, Li Zhang, Xiatian Zhu, Jianfeng Feng

However, a fundamental limitation is that their inference is very slow due to a need for many (e. g., 2000) iterations of sequential computations.

Diversity Image Generation

Accelerating Score-based Generative Models for High-Resolution Image Synthesis

no code implementations8 Jun 2022 Hengyuan Ma, Li Zhang, Xiatian Zhu, Jingfeng Zhang, Jianfeng Feng

To ensure stability of convergence in sampling and generation quality, however, this sequential sampling process has to take a small step size and many sampling iterations (e. g., 2000).

Image Generation Vocal Bursts Intensity Prediction

Clustering by the Probability Distributions from Extreme Value Theory

1 code implementation20 Feb 2022 Sixiao Zheng, Ke Fan, Yanxi Hou, Jianfeng Feng, Yanwei Fu

In contrast, the GPD fits the distribution of distance to the centroid exceeding a sufficiently large threshold, leading to a more stable performance of GPD k-means.

Clustering

SGM3D: Stereo Guided Monocular 3D Object Detection

1 code implementation3 Dec 2021 Zheyuan Zhou, Liang Du, Xiaoqing Ye, Zhikang Zou, Xiao Tan, Li Zhang, xiangyang xue, Jianfeng Feng

Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.

Autonomous Driving Depth Estimation +4

Sampling Before Training: Rethinking the Effect of Edges in the Process of Training Graph Neural Networks

no code implementations29 Sep 2021 Hengyuan Ma, Qi Yang, Bowen Sun, Long Shun, Junkui Li, Jianfeng Feng

Graph neural networks (GNN) demonstrate excellent performance on many graph-based tasks; however, they also impose a heavy computational burden when trained on a large-scale graph.

GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set

1 code implementation5 Feb 2021 Hanqing Chao, Kun Wang, Yiwei He, Junping Zhang, Jianfeng Feng

In this paper, we present a novel perspective that utilizes gait as a deep set, which means that a set of gait frames are integrated by a global-local fused deep network inspired by the way our left- and right-hemisphere processes information to learn information that can be used in identification.

Gait Recognition

3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection

no code implementations1 Mar 2020 Liang Du, Jingang Tan, xiangyang xue, Lili Chen, Hongkai Wen, Jianfeng Feng, Jiamao Li, Xiaolin Zhang

We propose a novel fast and robust 3D point clouds segmentation framework via coupled feature selection, named 3DCFS, that jointly performs semantic and instance segmentation.

3D Semantic Instance Segmentation feature selection +2

Extreme Value k-means Clustering

no code implementations25 Sep 2019 Sixiao Zheng, Yanxi Hou, Yanwei Fu, Jianfeng Feng

We thus propose a novel algorithm called Extreme Value k-means (EV k-means), including GEV k-means and GPD k-means.

Clustering Computational Efficiency

GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition

3 code implementations15 Nov 2018 Hanqing Chao, Yiwei He, Junping Zhang, Jianfeng Feng

In this paper we present a novel perspective, where a gait is regarded as a set consisting of independent frames.

Multiview Gait Recognition

Chi-square Generative Adversarial Network

1 code implementation ICML 2018 Chenyang Tao, Liqun Chen, Ricardo Henao, Jianfeng Feng, Lawrence Carin Duke

To assess the difference between real and synthetic data, Generative Adversarial Networks (GANs) are trained using a distribution discrepancy measure.

Generative Adversarial Network

Dual Skipping Networks

no code implementations CVPR 2018 Changmao Cheng, Yanwei Fu, Yu-Gang Jiang, Wei Liu, Wenlian Lu, Jianfeng Feng, xiangyang xue

Inspired by the recent neuroscience studies on the left-right asymmetry of the human brain in processing low and high spatial frequency information, this paper introduces a dual skipping network which carries out coarse-to-fine object categorization.

General Classification Object +1

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