Search Results for author: Xiaoshuai Hao

Found 18 papers, 5 papers with code

MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction

no code implementations5 Feb 2025 Xiaoshuai Hao, Yunfeng Diao, Mengchuan Wei, Yifan Yang, Peng Hao, Rong Yin, HUI ZHANG, Weiming Li, Shu Zhao, Yu Liu

To address these issues, we propose MapFusion, a novel multi-modal Bird's-Eye View (BEV) feature fusion method for map construction.

Autonomous Driving

MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception

no code implementations2 Jan 2025 Xiaoshuai Hao, Guanqun Liu, YuTing Zhao, Yuheng Ji, Mengchuan Wei, Haimei Zhao, Lingdong Kong, Rong Yin, Yu Liu

Multi-sensor fusion models play a crucial role in autonomous driving perception, particularly in tasks like 3D object detection and HD map construction.

3D Object Detection Autonomous Driving +3

KALAHash: Knowledge-Anchored Low-Resource Adaptation for Deep Hashing

1 code implementation27 Dec 2024 Shu Zhao, Tan Yu, Xiaoshuai Hao, Wenchao Ma, Vijaykrishnan Narayanan

Deep hashing has been widely used for large-scale approximate nearest neighbor search due to its storage and search efficiency.

Deep Hashing parameter-efficient fine-tuning

Communication-Efficient Personalized Federal Graph Learning via Low-Rank Decomposition

no code implementations18 Dec 2024 Ruyue Liu, Rong Yin, Xiangzhen Bo, Xiaoshuai Hao, Xingrui Zhou, Yong liu, Can Ma, Weiping Wang

By utilizing low-rank and sparse parameters along with compression techniques, CEFGL significantly reduces communication complexity.

Graph Learning

DWCL: Dual-Weighted Contrastive Learning for Multi-View Clustering

1 code implementation26 Nov 2024 Hanning Yuan, Zhihui Zhang, Qi Guo, Lianhua Chi, Sijie Ruan, Jinhui Pang, Xiaoshuai Hao

Specifically, to reduce the impact of unreliable cross-views, we introduce an innovative Best-Other (B-O) contrastive mechanism that enhances the representation of individual views at a low computational cost.

Clustering Contrastive Learning

ESC-MISR: Enhancing Spatial Correlations for Multi-Image Super-Resolution in Remote Sensing

no code implementations7 Nov 2024 Zhihui Zhang, Jinhui Pang, Jianan Li, Xiaoshuai Hao

Besides, we perform a random shuffle strategy for the sequential inputs of LR images to attenuate temporal dependencies and capture weak temporal correlations in the training stage.

Image Reconstruction Image Super-Resolution

FTF-ER: Feature-Topology Fusion-Based Experience Replay Method for Continual Graph Learning

1 code implementation28 Jul 2024 Jinhui Pang, Changqing Lin, Xiaoshuai Hao, Rong Yin, Zixuan Wang, Zhihui Zhang, Jinglin He, Huang Tai Sheng

Specifically, from an overall perspective to maximize the utilization of the entire graph data, we propose a highly complementary approach including both feature and global topological information, which can significantly improve the effectiveness of the sampled nodes.

class-incremental learning Class Incremental Learning +2

BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation

no code implementations26 Jul 2024 Peng Hao, Xiaobing Wang, Yingying Jiang, Hanchao Jia, Xiaoshuai Hao

To address this limitation, we propose a novel bidirectional conditioning factorization in a semantic-aligned space for SGG, enabling efficient and generalizable interaction between entities and predicates.

Graph Generation Scene Graph Generation

MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

no code implementations16 Jul 2024 Xiaoshuai Hao, Ruikai Li, HUI ZHANG, Dingzhe Li, Rong Yin, Sangil Jung, Seung-In Park, ByungIn Yoo, Haimei Zhao, Jing Zhang

To address this, we employ the Knowledge Distillation (KD) idea for efficient HD map construction for the first time and introduce a novel KD-based approach called MapDistill to transfer knowledge from a high-performance camera-LiDAR fusion model to a lightweight camera-only model.

Autonomous Driving Knowledge Distillation +1

Is Your HD Map Constructor Reliable under Sensor Corruptions?

no code implementations18 Jun 2024 Xiaoshuai Hao, Mengchuan Wei, Yifan Yang, Haimei Zhao, HUI ZHANG, Yi Zhou, Qiang Wang, Weiming Li, Lingdong Kong, Jing Zhang

These insights provide a pathway for developing more reliable HD map construction methods, which are essential for the advancement of autonomous driving technology.

Autonomous Driving Data Augmentation

DOR3D-Net: Dense Ordinal Regression Network for 3D Hand Pose Estimation

no code implementations20 Mar 2024 Yamin Mao, Zhihua Liu, Weiming Li, SoonYong Cho, Qiang Wang, Xiaoshuai Hao

Recently, dense regression methods have attracted increasing attention in 3D hand pose estimation task, which provide a low computational burden and high accuracy regression way by densely regressing hand joint offset maps.

3D Hand Pose Estimation regression

Team AcieLee: Technical Report for EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023

no code implementations15 Jun 2023 Yuqi Li, Yizhi Luo, Xiaoshuai Hao, Chuanguang Yang, Zhulin An, Dantong Song, Wei Yi

In this report, we describe the technical details of our submission to the EPIC-SOUNDS Audio-Based Interaction Recognition Challenge 2023, by Team "AcieLee" (username: Yuqi\_Li).

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