155 citations · 480 across the 21 of their papers we have counts for
21 papers
Efficient Test-Time Adaptation of Vision-Language Models
Adilbek Karmanov, Dayan Guan, Shijian Lu +2
Test-time adaptation with pre-trained vision-language models has attracted increasing attention for tackling distribution shifts during the test time. Though prior studies have ach…
3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds
Aoran Xiao, Jiaxing Huang, Weihao Xuan +6
Robust point cloud parsing under all-weather conditions is crucial to level-5 autonomy in autonomous driving. However, how to learn a universal 3D semantic segmentation (3DSS) mode…
PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds
Aoran Xiao, Jiaxing Huang, Dayan Guan +3
LiDAR point clouds, which are usually scanned by rotating LiDAR sensors continuously, capture precise geometry of the surrounding environment and are crucial to many autonomous det…
Domain Adaptive Video Segmentation via Temporal Pseudo Supervision
Yun Xing, Dayan Guan, Jiaxing Huang +1
Video semantic segmentation has achieved great progress under the supervision of large amounts of labelled training data. However, domain adaptive video segmentation, which can mit…
Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation
Dayan Guan, Jiaxing Huang, Aoran Xiao +1
Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images, which has witnessed impressive progress with the recent a…
Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
Aoran Xiao, Jiaxing Huang, Dayan Guan +3
Point cloud data have been widely explored due to its superior accuracy and robustness under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved very i…
Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
Jiaxing Huang, Dayan Guan, Aoran Xiao +1
Unsupervised domain adaptation aims to align a labeled source domain and an unlabeled target domain, but it requires to access the source data which often raises concerns in data p…
Domain Adaptive Video Segmentation via Temporal Consistency Regularization
Dayan Guan, Jiaxing Huang, Aoran Xiao +1
Video semantic segmentation is an essential task for the analysis and understanding of videos. Recent efforts largely focus on supervised video segmentation by learning from fully…
Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation
Aoran Xiao, Jiaxing Huang, Dayan Guan +2
Knowledge transfer from synthetic to real data has been widely studied to mitigate data annotation constraints in various computer vision tasks such as semantic segmentation. Howev…
Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment
Jiaxing Huang, Dayan Guan, Aoran Xiao +1
Contemporary domain adaptive semantic segmentation aims to address data annotation challenges by assuming that target domains are completely unannotated. However, annotating a few…
Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
Jiaxing Huang, Dayan Guan, Aoran Xiao +2
Instance contrast for unsupervised representation learning has achieved great success in recent years. In this work, we explore the idea of instance contrastive learning in unsuper…
RDA: Robust Domain Adaptation via Fourier Adversarial Attacking
Jiaxing Huang, Dayan Guan, Aoran Xiao +1
Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe ove…
Cross-View Regularization for Domain Adaptive Panoptic Segmentation
Jiaxing Huang, Dayan Guan, Aoran Xiao +1
Panoptic segmentation unifies semantic segmentation and instance segmentation which has been attracting increasing attention in recent years. However, most existing research was co…
FSDR: Frequency Space Domain Randomization for Domain Generalization
Jiaxing Huang, Dayan Guan, Aoran Xiao +1
Domain generalization aims to learn a generalizable model from a known source domain for various unknown target domains. It has been studied widely by domain randomization that tra…
MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation
Jiaxing Huang, Dayan Guan, Shijian Lu +1
Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial l…
FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation
Aoran Xiao, Xiaofei Yang, Shijian Lu +2
Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-c…
Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection
Dayan Guan, Jiaxing Huang, Aoran Xiao +2
Unsupervised domain adaptive object detection aims to adapt detectors from a labelled source domain to an unlabelled target domain. Most existing works take a two-stage strategy th…
Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
Jiaxing Huang, Shijian Lu, Dayan Guan +1
Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations. However, most exis…
Unsupervised Domain Adaptation for Multispectral Pedestrian Detection
Dayan Guan, Xing Luo, Yanpeng Cao +4
Multimodal information (e.g., visible and thermal) can generate robust pedestrian detections to facilitate around-the-clock computer vision applications, such as autonomous driving…
Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection
Yanpeng Cao, Dayan Guan, Yulun Wu +3
Effective fusion of complementary information captured by multi-modal sensors (visible and infrared cameras) enables robust pedestrian detection under various surveillance situatio…
Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection
Dayan Guan, Yanpeng Cao, Jun Liang +2
Multispectral pedestrian detection has received extensive attention in recent years as a promising solution to facilitate robust human target detection for around-the-clock applica…