Search Results for author: Lin Zhao

Found 27 papers, 6 papers with code

Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations

no code implementations22 Jun 2022 Lin Zhao, Haixing Dai, Zihao Wu, Zhenxiang Xiao, Lu Zhang, David Weizhong Liu, Xintao Hu, Xi Jiang, Sheng Li, Dajiang Zhu, Tianming Liu

However, whether there exists semantic correlations/connections between the visual representations in ANNs and those in BNNs remains largely unexplored due to both the lack of an effective tool to link and couple two different domains, and the lack of a general and effective framework of representing the visual semantics in BNNs such as human functional brain networks (FBNs).

Image Classification Representation Learning

Neural Moving Horizon Estimation for Robust Flight Control

1 code implementation21 Jun 2022 Bingheng Wang, Zhengtian Ma, Shupeng Lai, Lin Zhao

Estimating and reacting to external disturbances is crucial for robust flight control of quadrotors.

Rectify ViT Shortcut Learning by Visual Saliency

no code implementations17 Jun 2022 Chong Ma, Lin Zhao, Yuzhong Chen, David Weizhong Liu, Xi Jiang, Tuo Zhang, Xintao Hu, Dinggang Shen, Dajiang Zhu, Tianming Liu

In this work, we propose a novel and effective saliency-guided vision transformer (SGT) model to rectify shortcut learning in ViT with the absence of eye-gaze data.

Invertible Sharpening Network for MRI Reconstruction Enhancement

no code implementations6 Jun 2022 Siyuan Dong, Eric Z. Chen, Lin Zhao, Xiao Chen, Yikang Liu, Terrence Chen, Shanhui Sun

During inference, the learned blurring transform can be inverted to a sharpening transform leveraging the network's invertibility.

MRI Reconstruction SSIM

Representing Brain Anatomical Regularity and Variability by Few-Shot Embedding

no code implementations26 May 2022 Lu Zhang, Xiaowei Yu, Yanjun Lyu, Zhengwang Wu, Haixing Dai, Lin Zhao, Li Wang, Gang Li, Tianming Liu, Dajiang Zhu

Our experimental results show that: 1) the learned embedding vectors can quantitatively encode the commonality and individuality of cortical folding patterns; 2) with the embeddings we can robustly infer the complicated many-to-many anatomical correspondences among different brains and 3) our model can be successfully transferred to new populations with very limited training samples.

Few-Shot Learning

Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning

no code implementations25 May 2022 Chong Ma, Lin Zhao, Yuzhong Chen, Lu Zhang, Zhenxiang Xiao, Haixing Dai, David Liu, Zihao Wu, Zhengliang Liu, Sheng Wang, Jiaxing Gao, Changhe Li, Xi Jiang, Tuo Zhang, Qian Wang, Dinggang Shen, Dajiang Zhu, Tianming Liu

To address this problem, we propose to infuse human experts' intelligence and domain knowledge into the training of deep neural networks.

Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning

no code implementations20 May 2022 Yuzhong Chen, Zhenxiang Xiao, Lin Zhao, Lu Zhang, Haixing Dai, David Weizhong Liu, Zihao Wu, Changhe Li, Tuo Zhang, Changying Li, Dajiang Zhu, Tianming Liu, Xi Jiang

However, for data-intensive models such as vision transformer (ViT), current fine-tuning based FSL approaches are inefficient in knowledge generalization and thus degenerate the downstream task performances.

Active Learning Few-Shot Learning

A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformers

no code implementations20 May 2022 Yuzhong Chen, Yu Du, Zhenxiang Xiao, Lin Zhao, Lu Zhang, David Weizhong Liu, Dajiang Zhu, Tuo Zhang, Xintao Hu, Tianming Liu, Xi Jiang

The key characteristic of these ViT models is to adopt different aggregation strategies of spatial patch information within the artificial neural networks (ANNs).

Disentangling Spatial-Temporal Functional Brain Networks via Twin-Transformers

no code implementations20 Apr 2022 Xiaowei Yu, Lu Zhang, Lin Zhao, Yanjun Lyu, Tianming Liu, Dajiang Zhu

In this work, we propose a novel Twin-Transformers framework to simultaneously infer common and individual functional networks in both spatial and temporal space, in a self-supervised manner.

Faster Non-asymptotic Convergence for Double Q-learning

no code implementations NeurIPS 2021 Lin Zhao, Huaqing Xiong, Yingbin Liang

This paper tackles the more challenging case of a constant learning rate, and develops new analytical tools that improve the existing convergence rate by orders of magnitude.

Q-Learning

MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification

2 code implementations27 Oct 2021 Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni

We introduce MedMNIST v2, a large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D.

AutoML Image Classification

LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation

no code implementations17 Aug 2021 Lin Zhao, Hui Zhou, Xinge Zhu, Xiao Song, Hongsheng Li, Wenbing Tao

However, two major issues of the fusion between camera and LiDAR hinder its performance, \ie, how to effectively fuse these two modalities and how to precisely align them (suffering from the weak spatiotemporal synchronization problem).

Autonomous Driving LIDAR Semantic Segmentation +1

Double Q-learning: New Analysis and Sharper Finite-time Bound

no code implementations1 Jan 2021 Lin Zhao, Huaqing Xiong, Yingbin Liang, Wei zhang

Double Q-learning (Hasselt 2010) has gained significant success in practice due to its effectiveness in overcoming the overestimation issue of Q-learning.

Q-Learning

Origin of the Electronic Structure in Single-Layer FeSe/SrTiO3 Films

no code implementations16 Dec 2020 Defa Liu, Xianxin Wu, Fangsen Li, Yong Hu, Jianwei Huang, Yu Xu, Cong Li, Yunyi Zang, Junfeng He, Lin Zhao, Shaolong He, Chenjia Tang, Zhi Li, Lili Wang, Qingyan Wang, Guodong Liu, Zuyan Xu, Xu-Cun Ma, Qi-Kun Xue, Jiangping Hu, X. J. Zhou

These observations not only show the first direct evidence that the electronic structure of single-layer FeSe/SrTiO3 films originates from bulk FeSe through a combined effect of an electronic phase transition and an interfacial charge transfer, but also provide a quantitative basis for theoretical models in describing the electronic structure and understanding the superconducting mechanism in single-layer FeSe/SrTiO3 films.

Band Gap Superconductivity Strongly Correlated Electrons

Finite-Time Analysis for Double Q-learning

no code implementations NeurIPS 2020 Huaqing Xiong, Lin Zhao, Yingbin Liang, Wei zhang

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values incurred by random sampling.

Q-Learning

Momentum Q-learning with Finite-Sample Convergence Guarantee

no code implementations30 Jul 2020 Bowen Weng, Huaqing Xiong, Lin Zhao, Yingbin Liang, Wei zhang

For the infinite state-action space case, we establish the convergence guarantee for MomentumQ with linear function approximations and Markovian sampling.

Q-Learning

JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds

2 code implementations20 Dec 2019 Lin Zhao, Wenbing Tao

In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously.

3D Instance Segmentation Semantic Segmentation

Localization-aware Channel Pruning for Object Detection

no code implementations6 Nov 2019 Zihao Xie, Wenbing Tao, Li Zhu, Lin Zhao

In this paper, based on discrimination-aware channel pruning (DCP) which is state-of-the-art pruning method for classification, we propose a localization-aware auxiliary network to find out the channels with key information for classification and regression so that we can conduct channel pruning directly for object detection, which saves lots of time and computing resources.

Classification General Classification +3

Data-based wind disaster climate identification algorithm and extreme wind speed prediction

no code implementations29 Aug 2019 Wei Cui, Teng Ma, Lin Zhao, Yaojun Ge

Based on classification results, the extreme wind speeds calculated based on mixed wind hazard types is compared with those obtained from conventional methods, and the effects on structural design for different return periods are discussed.

Improving Slot Filling in Spoken Language Understanding with Joint Pointer and Attention

1 code implementation ACL 2018 Lin Zhao, Zhe Feng

We present a generative neural network model for slot filling based on a sequence-to-sequence (Seq2Seq) model together with a pointer network, in the situation where only sentence-level slot annotations are available in the spoken dialogue data.

Slot Filling Speech Recognition +1

Structure-Infused Copy Mechanisms for Abstractive Summarization

1 code implementation COLING 2018 Kaiqiang Song, Lin Zhao, Fei Liu

In this paper, we present structure-infused copy mechanisms to facilitate copying important words and relations from the source sentence to summary sentence.

Abstractive Text Summarization

A unified integral equation scheme for doubly-periodic Laplace and Stokes boundary value problems in two dimensions

2 code implementations24 Nov 2016 Alex H. Barnett, Gary Marple, Shravan Veerapaneni, Lin Zhao

We present a spectrally-accurate scheme to turn a boundary integral formulation for an elliptic PDE on a single unit cell geometry into one for the fully periodic problem.

Numerical Analysis 65N38, 65N80, 76D07, 76M50

Question Generation from a Knowledge Base with Web Exploration

no code implementations12 Oct 2016 Linfeng Song, Lin Zhao

Question generation from a knowledge base (KB) is the task of generating questions related to the domain of the input KB.

Natural Questions Question Generation

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