Search Results for author: Dayan Guan

Found 22 papers, 16 papers with code

BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models

2 code implementations5 Dec 2023 Rizhao Cai, Zirui Song, Dayan Guan, Zhenhao Chen, Xing Luo, Chenyu Yi, Alex Kot

Large Multimodal Models (LMMs) such as GPT-4V and LLaVA have shown remarkable capabilities in visual reasoning with common image styles.

Benchmarking Visual Question Answering +1

Noise-Tolerant Unsupervised Adapter for Vision-Language Models

no code implementations26 Sep 2023 Eman Ali, Dayan Guan, Shijian Lu, Abdulmotaleb Elsaddik

NtUA works as a key-value cache that formulates visual features and predicted pseudo-labels of the few-shot unlabelled target samples as key-value pairs.

Image Classification Knowledge Distillation +2

3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds

1 code implementation CVPR 2023 Aoran Xiao, Jiaxing Huang, Weihao Xuan, Ruijie Ren, Kangcheng Liu, Dayan Guan, Abdulmotaleb El Saddik, Shijian Lu, Eric Xing

In addition, we design a domain randomization technique that alternatively randomizes the geometry styles of point clouds and aggregates their embeddings, ultimately leading to a generalizable model that can improve 3DSS under various adverse weather effectively.

3D Semantic Segmentation Autonomous Driving

Domain Adaptive Video Segmentation via Temporal Pseudo Supervision

1 code implementation6 Jul 2022 Yun Xing, Dayan Guan, Jiaxing Huang, Shijian Lu

Specifically, we design cross-frame pseudo labelling to provide pseudo supervision from previous video frames while learning from the augmented current video frames.

Segmentation Semantic Segmentation +2

Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation

1 code implementation CVPR 2022 Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu

We build the balanced subclass distributions by clustering pixels of each original class into multiple subclasses of similar sizes, which provide class-balanced pseudo supervision to regularize the class-biased segmentation.

Segmentation Semi-Supervised Semantic Segmentation

Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey

1 code implementation28 Feb 2022 Aoran Xiao, Jiaxing Huang, Dayan Guan, Xiaoqin Zhang, Shijian Lu, Ling Shao

The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data.

Autonomous Driving Representation Learning

Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data

1 code implementation NeurIPS 2021 Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

To this end, we design an innovative historical contrastive learning (HCL) technique that exploits historical source hypothesis to make up for the absence of source data in UMA.

Contrastive Learning Unsupervised Domain Adaptation

Domain Adaptive Video Segmentation via Temporal Consistency Regularization

1 code implementation ICCV 2021 Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu

This paper presents DA-VSN, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos.

Segmentation Unsupervised Domain Adaptation +1

Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation

1 code implementation12 Jul 2021 Aoran Xiao, Jiaxing Huang, Dayan Guan, Fangneng Zhan, Shijian Lu

Extensive experiments show that SynLiDAR provides a high-quality data source for studying 3D transfer and the proposed PCT achieves superior point cloud translation consistently across the three setups.

3D Unsupervised Domain Adaptation Data Augmentation +5

Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment

no code implementations5 Jun 2021 Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

We position the few labeled target samples as references that gauge the similarity between source and target features and guide adaptive inter-domain alignment for learning more similar source features.

Domain Adaptation Image Classification +4

RDA: Robust Domain Adaptation via Fourier Adversarial Attacking

1 code implementation ICCV 2021 Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

With FAA-generated samples, the training can continue the 'random walk' and drift into an area with a flat loss landscape, leading to more robust domain adaptation.

Unsupervised Domain Adaptation

Category Contrast for Unsupervised Domain Adaptation in Visual Tasks

1 code implementation CVPR 2022 Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu, Ling Shao

In this work, we explore the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and propose a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.

Contrastive Learning Representation Learning +1

MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

no code implementations24 Mar 2021 Jiaxing Huang, Dayan Guan, Shijian Lu, Aoran Xiao

Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation.

Image-to-Image Translation Semantic Segmentation +2

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

1 code implementation CVPR 2021 Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

The inter-task regularization exploits the complementary nature of instance segmentation and semantic segmentation and uses it as a constraint for better feature alignment across domains.

Domain Adaptation Instance Segmentation +2

FSDR: Frequency Space Domain Randomization for Domain Generalization

1 code implementation CVPR 2021 Jiaxing Huang, Dayan Guan, Aoran Xiao, Shijian Lu

It has been studied widely by domain randomization that transfers source images to different styles in spatial space for learning domain-agnostic features.

Domain Generalization

FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation

1 code implementation1 Mar 2021 Aoran Xiao, Xiaofei Yang, Shijian Lu, Dayan Guan, Jiaxing Huang

Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively.

3D Semantic Segmentation Point Cloud Segmentation +2

Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection

3 code implementations27 Feb 2021 Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu, Yanpeng Cao

Specifically, we design an uncertainty metric that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively.

Object object-detection +2

Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation

1 code implementation ECCV 2020 Jiaxing Huang, Shijian Lu, Dayan Guan, Xiaobing Zhang

Recent advances in unsupervised domain adaptation for semantic segmentation have shown great potentials to relieve the demand of expensive per-pixel annotations.

Relation Segmentation +2

Unsupervised Domain Adaptation for Multispectral Pedestrian Detection

no code implementations7 Apr 2019 Dayan Guan, Xing Luo, Yanpeng Cao, Jiangxin Yang, Yanlong Cao, George Vosselman, Michael Ying Yang

In this paper, we propose a novel unsupervised domain adaptation framework for multispectral pedestrian detection, by iteratively generating pseudo annotations and updating the parameters of our designed multispectral pedestrian detector on target domain.

Autonomous Driving Pedestrian Detection +1

Box-level Segmentation Supervised Deep Neural Networks for Accurate and Real-time Multispectral Pedestrian Detection

no code implementations14 Feb 2019 Yanpeng Cao, Dayan Guan, Yulun Wu, Jiangxin Yang, Yanlong Cao, Michael Ying Yang

Effective fusion of complementary information captured by multi-modal sensors (visible and infrared cameras) enables robust pedestrian detection under various surveillance situations (e. g. daytime and nighttime).

Autonomous Driving Computational Efficiency +1

Fusion of Multispectral Data Through Illumination-aware Deep Neural Networks for Pedestrian Detection

no code implementations27 Feb 2018 Dayan Guan, Yanpeng Cao, Jun Liang, Yanlong Cao, Michael Ying Yang

Moreover, we utilized illumination information together with multispectral data to generate more accurate semantic segmentation which are used to boost pedestrian detection accuracy.

Autonomous Driving Multi-Task Learning +2

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