Search Results for author: Liang Xiao

Found 33 papers, 16 papers with code

An End-to-End Robust Point Cloud Semantic Segmentation Network with Single-Step Conditional Diffusion Models

1 code implementation25 Nov 2024 Wentao Qu, Jing Wang, Yongshun Gong, Xiaoshui Huang, Liang Xiao

Existing conditional Denoising Diffusion Probabilistic Models (DDPMs) with a Noise-Conditional Framework (NCF) remain challenging for 3D scene understanding tasks, as the complex geometric details in scenes increase the difficulty of fitting the gradients of the data distribution (the scores) from semantic labels.

Denoising Scene Understanding +1

TSBP: Improving Object Detection in Histology Images via Test-time Self-guided Bounding-box Propagation

1 code implementation25 Sep 2024 Tingting Yang, Liang Xiao, Yizhe Zhang

Because of this, using a preset global threshold (e. g., 0. 5) applied to all the bounding box candidates may lead to suboptimal solutions.

Cell Detection object-detection +1

Advancing Prompt Learning through an External Layer

no code implementations29 Jul 2024 Fangming Cui, Xun Yang, Chao Wu, Liang Xiao, Xinmei Tian

Specifically, we propose a textual external layer and learnable visual embeddings for adapting VLMs to downstream tasks.

Few-Shot Learning valid

DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

no code implementations CVPR 2024 Chen Min, Dawei Zhao, Liang Xiao, Jian Zhao, Xinli Xu, Zheng Zhu, Lei Jin, Jianshu Li, Yulan Guo, Junliang Xing, Liping Jing, Yiming Nie, Bin Dai

In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal fashion.

3D Object Detection Motion Forecasting +4

Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond

1 code implementation6 May 2024 Zheng Zhu, XiaoFeng Wang, Wangbo Zhao, Chen Min, Nianchen Deng, Min Dou, Yuqi Wang, Botian Shi, Kai Wang, Chi Zhang, Yang You, Zhaoxiang Zhang, Dawei Zhao, Liang Xiao, Jian Zhao, Jiwen Lu, Guan Huang

General world models represent a crucial pathway toward achieving Artificial General Intelligence (AGI), serving as the cornerstone for various applications ranging from virtual environments to decision-making systems.

Autonomous Driving Decision Making +2

CoSD: Collaborative Stance Detection with Contrastive Heterogeneous Topic Graph Learning

no code implementations26 Apr 2024 Yinghan Cheng, Qi Zhang, Chongyang Shi, Liang Xiao, Shufeng Hao, Liang Hu

To address these challenges, we present a novel collaborative stance detection framework called (CoSD) which leverages contrastive heterogeneous topic graph learning to learn topic-aware semantics and collaborative signals among texts, topics, and stance labels for enhancing stance detection.

Graph Learning Stance Detection

ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes

no code implementations10 Mar 2024 Shengxin Hong, Liang Xiao, Xin Zhang, Jianxia Chen

We construct a formal model of ArgMed-Agents and present conjectures for theoretical guarantees.

MSynFD: Multi-hop Syntax aware Fake News Detection

no code implementations18 Feb 2024 Liang Xiao, Qi Zhang, Chongyang Shi, Shoujin Wang, Usman Naseem, Liang Hu

These existing methods fail to handle the complex, subtle twists in news articles, such as syntax-semantics mismatches and prior biases, leading to lower performance and potential failure when modalities or social context are missing.

Fake News Detection

A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling

1 code implementation CVPR 2024 Wentao Qu, Yuantian Shao, Lingwu Meng, Xiaoshui Huang, Liang Xiao

Most of the existing point cloud upsampling methods focus on sparse point cloud feature extraction and upsampling module design.

Denoising point cloud upsampling

Adversarial Purification of Information Masking

1 code implementation26 Nov 2023 Sitong Liu, Zhichao Lian, Shuangquan Zhang, Liang Xiao

Notably, the residual perturbations on the purified image primarily stem from the same-position patch and similar patches of the adversarial sample.

Adversarial Attack Adversarial Purification

A Spectral Diffusion Prior for Hyperspectral Image Super-Resolution

1 code implementation15 Nov 2023 Jianjun Liu, Zebin Wu, Liang Xiao

Motivated by the success of diffusion models, we propose a novel spectral diffusion prior for fusion-based HSI super-resolution.

Hyperspectral Image Super-Resolution Image Super-Resolution

UniWorld: Autonomous Driving Pre-training via World Models

no code implementations14 Aug 2023 Chen Min, Dawei Zhao, Liang Xiao, Yiming Nie, Bin Dai

In this paper, we draw inspiration from Alberto Elfes' pioneering work in 1989, where he introduced the concept of the occupancy grid as World Models for robots.

3D Object Detection Autonomous Driving +2

UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving

2 code implementations30 May 2023 Chen Min, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai

When compared to monocular pre-training methods on the nuScenes dataset, UniScene shows a significant improvement of about 2. 0% in mAP and 2. 0% in NDS for multi-camera 3D object detection, as well as a 3% increase in mIoU for surrounding semantic scene completion.

3D Object Detection 3D Scene Reconstruction +2

Adversarial and Random Transformations for Robust Domain Adaptation and Generalization

no code implementations13 Nov 2022 Liang Xiao, Jiaolong Xu, Dawei Zhao, Erke Shang, Qi Zhu, Bin Dai

In this work, we show that by simply applying consistency training with random data augmentation, state-of-the-art results on domain adaptation (DA) and generalization (DG) can be obtained.

Data Augmentation Domain Adaptation

Automatic Check-Out via Prototype-based Classifier Learning from Single-Product Exemplars

4 code implementations The European Conference on Computer Vision (ECCV) 2022 Hao Chen, Xiu-Shen Wei, Faen Zhang, Yang shen, Hui Xu, Liang Xiao

Automatic Check-Out (ACO) aims to accurately predict the presence and count of each category of products in check-out images, where a major challenge is the significant domain gap between training data (single-product exemplars) and test data (check-out images).

Re-Ranking

ORFD: A Dataset and Benchmark for Off-Road Freespace Detection

2 code implementations20 Jun 2022 Chen Min, Weizhong Jiang, Dawei Zhao, Jiaolong Xu, Liang Xiao, Yiming Nie, Bin Dai

Freespace detection is an essential component of autonomous driving technology and plays an important role in trajectory planning.

Autonomous Driving Semantic Segmentation +1

Occupancy-MAE: Self-supervised Pre-training Large-scale LiDAR Point Clouds with Masked Occupancy Autoencoders

2 code implementations20 Jun 2022 Chen Min, Xinli Xu, Dawei Zhao, Liang Xiao, Yiming Nie, Bin Dai

This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE).

3D Object Detection 3D Semantic Segmentation +6

Block shuffling learning for Deepfake Detection

1 code implementation6 Feb 2022 Sitong Liu, Zhichao Lian, Siqi Gu, Liang Xiao

Finally, we restore the spatial layout of the blocks to capture the semantic associations among them.

DeepFake Detection Face Detection +1

Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution

no code implementations22 Oct 2021 Jianjun Liu, Zebin Wu, Liang Xiao, Xiao-Jun Wu

Inspired by the specific properties of model, we make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner.

Decoder Hyperspectral Image Super-Resolution +1

Trajectory Prediction for Autonomous Driving with Topometric Map

1 code implementation9 May 2021 Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai

The experimental results show that the proposed method outperforms state-of-the-art multimodal methods and is robust to the perturbations of the topometric map.

Autonomous Driving Trajectory Prediction

Attentional Graph Neural Network for Parking-slot Detection

1 code implementation6 Apr 2021 Chen Min, Jiaolong Xu, Liang Xiao, Dawei Zhao, Yiming Nie, Bin Dai

Deep learning has recently demonstrated its promising performance for vision-based parking-slot detection.

Graph Neural Network

Privacy-Preserving Federated Learning for UAV-Enabled Networks: Learning-Based Joint Scheduling and Resource Management

no code implementations28 Nov 2020 Helin Yang, Jun Zhao, Zehui Xiong, Kwok-Yan Lam, Sumei Sun, Liang Xiao

However, due to the privacy concerns of devices and limited computation or communication resource of UAVs, it is impractical to send raw data of devices to UAV servers for model training.

Distributed Computing Federated Learning +3

Sparse Coding Driven Deep Decision Tree Ensembles for Nuclear Segmentation in Digital Pathology Images

no code implementations13 Aug 2020 Jie Song, Liang Xiao, Mohsen Molaei, Zhichao Lian

In this way, rich image appearance models together with more contextual information are integrated by learning a series of decision tree ensembles.

Image Segmentation Nuclear Segmentation +2

Efficient Deep Learning of Non-local Features for Hyperspectral Image Classification

1 code implementation2 Aug 2020 Yu Shen, Sijie Zhu, Chen Chen, Qian Du, Liang Xiao, Jianyu Chen, Delu Pan

Therefore, to incorporate the long-range contextual information, a deep fully convolutional network (FCN) with an efficient non-local module, named ENL-FCN, is proposed for HSI classification.

Deep Learning General Classification +1

Deep Reinforcement Learning Based Intelligent Reflecting Surface for Secure Wireless Communications

no code implementations27 Feb 2020 Helin Yang, Zehui Xiong, Jun Zhao, Dusit Niyato, Liang Xiao, Qingqing Wu

As the system is highly dynamic and complex, and it is challenging to address the non-convex optimization problem, a novel deep reinforcement learning (DRL)-based secure beamforming approach is firstly proposed to achieve the optimal beamforming policy against eavesdroppers in dynamic environments.

Deep Reinforcement Learning reinforcement-learning +1

Fast Reinforcement Learning for Anti-jamming Communications

no code implementations13 Feb 2020 Pei-Gen Ye, Yuan-Gen Wang, Jin Li, Liang Xiao

This letter presents a fast reinforcement learning algorithm for anti-jamming communications which chooses previous action with probability $\tau$ and applies $\epsilon$-greedy with probability $(1-\tau)$.

reinforcement-learning Reinforcement Learning +1

Self-supervised Domain Adaptation for Computer Vision Tasks

1 code implementation25 Jul 2019 Jiaolong Xu, Liang Xiao, Antonio M. Lopez

Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy on semantic segmentation within our method, consisting of prediction layer alignment and batch normalization calibration.

Domain Adaptation Object Recognition +3

Secure Mobile Crowdsensing with Deep Learning

no code implementations23 Jan 2018 Liang Xiao, Donghua Jiang, Dongjin Xu, Ning An

In order to stimulate secure sensing for Internet of Things (IoT) applications such as healthcare and traffic monitoring, mobile crowdsensing (MCS) systems have to address security threats, such as jamming, spoofing and faked sensing attacks, during both the sensing and the information exchange processes in large-scale dynamic and heterogenous networks.

Deep Learning Intrusion Detection

Reinforcement Learning-based Energy Trading for Microgrids

no code implementations19 Jan 2018 Liang Xiao, Xingyu Xiao, Canhuang Dai, Mugen Pengy, Li-Chun Wang, H. Vincent Poor

The Nash quilibrium (NE) of the game is provided, revealing the conditions under which the local energy generation satisfies the energy demand of the MG and providing the performance bound of the energy trading scheme.

Systems and Control

Two-dimensional Anti-jamming Mobile Communication Based on Reinforcement Learning

no code implementations19 Dec 2017 Liang Xiao, Guoan Han, Donghua Jiang, Hongzi Zhu, Yanyong Zhang, H. Vincent Poor

It is shown that, by applying reinforcement learning techniques, a mobile device can achieve an optimal communication policy without the need to know the jamming and interference model and the radio channel model in a dynamic game framework.

reinforcement-learning Reinforcement Learning +2

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