Search Results for author: Man-on Pun

Found 18 papers, 15 papers with code

Kolmogorov-Arnold Network for Remote Sensing Image Semantic Segmentation

1 code implementation13 Jan 2025 Xianping Ma, Ziyao Wang, Yin Hu, Xiaokang Zhang, Man-on Pun

Semantic segmentation plays a crucial role in remote sensing applications, where the accurate extraction and representation of features are essential for high-quality results.

Decoder Segmentation +1

MANet: Fine-Tuning Segment Anything Model for Multimodal Remote Sensing Semantic Segmentation

1 code implementation15 Oct 2024 Xianping Ma, Xiaokang Zhang, Man-on Pun, Bo Huang

Building upon recent advancements in vision foundation models, particularly the Segment Anything Model (SAM), this study introduces a novel Multimodal Adapter-based Network (MANet) for multimodal remote sensing semantic segmentation.

General Knowledge Segmentation +1

iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement

2 code implementations8 Jul 2024 Aoyu Pang, Maonan Wang, Man-on Pun, Chung Shue Chen, Xi Xiong

However, the existing RL-based TSC system often overlooks imperfect observations caused by degraded communication, such as packet loss, delays, and noise, as well as rare real-life events not included in the reward function, such as unconsidered emergency vehicles.

Language Modeling Language Modelling +3

Traffic Signal Cycle Control with Centralized Critic and Decentralized Actors under Varying Intervention Frequencies

1 code implementation12 Jun 2024 Maonan Wang, YiRong Chen, Yuheng Kan, Chengcheng Xu, Michael Lepech, Man-on Pun, Xi Xiong

Traffic congestion in urban areas is a significant problem, leading to prolonged travel times, reduced efficiency, and increased environmental concerns.

Traffic Signal Control

Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation

1 code implementation6 Apr 2024 Xianping Ma, Xiaokang Zhang, Xingchen Ding, Man-on Pun, Siwei Ma

Unsupervised domain adaptation (UDA) techniques are vital for semantic segmentation in geosciences, effectively utilizing remote sensing imagery across diverse domains.

Generative Adversarial Network Representation Learning +3

RS3Mamba: Visual State Space Model for Remote Sensing Images Semantic Segmentation

1 code implementation3 Apr 2024 Xianping Ma, Xiaokang Zhang, Man-on Pun

Experimental results on two widely used datasets, ISPRS Vaihingen and LoveDA Urban, demonstrate the effectiveness and potential of the proposed RS3Mamba.

Long-range modeling Mamba +2

Adaptive Semantic-Enhanced Denoising Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution

1 code implementation17 Mar 2024 Jialu Sui, Xianping Ma, Xiaokang Zhang, Man-on Pun

However, the high-frequency details generated by DDPM often suffer from misalignment with HR images due to the model's tendency to overlook long-range semantic contexts.

Decoder Denoising +2

DF4LCZ: A SAM-Empowered Data Fusion Framework for Scene-Level Local Climate Zone Classification

1 code implementation14 Mar 2024 Qianqian Wu, Xianping Ma, Jialu Sui, Man-on Pun

The proposed method introduces a novel Dual-stream Fusion framework for LCZ classification (DF4LCZ), integrating instance-based location features from Google imagery with the scene-level spatial-spectral features extracted from Sentinel-2 imagery.

LLM-Assisted Light: Leveraging Large Language Model Capabilities for Human-Mimetic Traffic Signal Control in Complex Urban Environments

1 code implementation13 Mar 2024 Maonan Wang, Aoyu Pang, Yuheng Kan, Man-on Pun, Chung Shue Chen, Bo Huang

Specifically, a hybrid framework that augments LLMs with a suite of perception and decision-making tools is proposed, facilitating the interrogation of both the static and dynamic traffic information.

Decision Making Language Modeling +5

Diffusion Enhancement for Cloud Removal in Ultra-Resolution Remote Sensing Imagery

1 code implementation25 Jan 2024 Jialu Sui, Yiyang Ma, Wenhan Yang, Xiaokang Zhang, Man-on Pun, Jiaying Liu

The presence of cloud layers severely compromises the quality and effectiveness of optical remote sensing (RS) images.

Cloud Removal Image Generation

UniTSA: A Universal Reinforcement Learning Framework for V2X Traffic Signal Control

1 code implementation8 Dec 2023 Maonan Wang, Xi Xiong, Yuheng Kan, Chengcheng Xu, Man-on Pun

Traffic congestion is a persistent problem in urban areas, which calls for the development of effective traffic signal control (TSC) systems.

reinforcement-learning Reinforcement Learning (RL) +1

SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints

2 code implementations5 Dec 2023 Xianping Ma, Qianqian Wu, Xingyu Zhao, Xiaokang Zhang, Man-on Pun, Bo Huang

Furthermore, the boundary loss capitalizes on the distinctive features of SGB by directing the model's attention to the boundary information of the object.

Model Optimization Novel Concepts +4

GCD-DDPM: A Generative Change Detection Model Based on Difference-Feature Guided DDPM

1 code implementation6 Jun 2023 Yihan Wen, Xianping Ma, Xiaokang Zhang, Man-on Pun

Furthermore, the Difference Conditional Encoder (DCE), is designed to guide the generation of CD maps by exploiting multi-level difference features.

Change Detection Denoising +2

GCRDN: Global Context-Driven Residual Dense Network for Remote Sensing Image Superresolution

1 code implementation Jounal 2023 Jialu Sui, Xianping Ma, Xiaokang Zhang, Man-on Pun

To cope with this problem, this work proposes a novel global context-driven residual dense network (GCRDN) for satellite image SR based on the encoder and decoder architecture.

Decoder Image Reconstruction +1

ADLight: A Universal Approach of Traffic Signal Control with Augmented Data Using Reinforcement Learning

1 code implementation24 Oct 2022 Maonan Wang, Yutong Xu, Xi Xiong, Yuheng Kan, Chengcheng Xu, Man-on Pun

In this paper, we propose a novel reinforcement learning approach with augmented data (ADLight) to train a universal model for intersections with different structures.

Data Augmentation reinforcement-learning +3

Rényi State Entropy for Exploration Acceleration in Reinforcement Learning

no code implementations8 Mar 2022 Mingqi Yuan, Man-on Pun, Dong Wang

One of the most critical challenges in deep reinforcement learning is to maintain the long-term exploration capability of the agent.

Deep Reinforcement Learning reinforcement-learning +1

Fairness-Oriented User Scheduling for Bursty Downlink Transmission Using Multi-Agent Reinforcement Learning

no code implementations30 Dec 2020 Mingqi Yuan, Qi Cao, Man-on Pun, Yi Chen

In this work, we develop practical user scheduling algorithms for downlink bursty traffic with emphasis on user fairness.

Distributed Optimization Fairness +3

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