Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Michael Ying YangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works44 from public data
- Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection343
This paper demonstrates illumination information encoded in multispectral images can be utilized to significantly boost performance of pedestrian detection and presents a powerful framework based on multi-task learning of illumination-aware pedestrians detection and semantic segmentation.
- FSDR: Frequency Space Domain Randomization for Domain Generalization320
Frequency Space Domain Randomization (FSDR) is proposed that randomizes images in frequency space by keeping domain-invariant FCs (DIFs) and randomizing domain-variant FC's (DVFs) only and designed a network that can identify and fuse DIFs and DVFs dynamically through iterative learning.
- Efficient Test-Time Adaptation of Vision-Language Models187
TDA is designed, a training-free dynamic adapter that enables effective and efficient test-time adaptation with vision-language models and introduces negative pseudo labeling that alleviates the adverse impact of pseudo label noises.
- Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation169
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.
- Category Contrast for Unsupervised Domain Adaptation in Visual Tasks160
This work explores the idea of instance contrastive learning in unsupervised domain adaptation (UDA) and proposes a novel Category Contrast technique (CaCo) that introduces semantic priors on top of instance discrimination for visual UDA tasks.
- Unsupervised Point Cloud Representation Learning With Deep Neural Networks: A Survey155
This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs and quantitatively benchmark and discuss the reviewed methods over multiple widely adopted point cloud datasets.
- Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection151
An uncertainty metric is designed that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively and is exploited to achieve curriculum learning that first performs easier image-level alignment and then more difficult instance- level alignment progressively.
- 148
- Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation133
The proposed CrCDA learns and enforces the prototypical local contextual-relations explicitly in the feature space of a labelled source domain while transferring them to an unlabelled target domain via backpropagation-based adversarial learning.
- 95
- RDA: Robust Domain Adaptation via Fourier Adversarial Attacking89
RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA, is presented and extensive experiments over multiple domain adaptation tasks show that RDA can work with different computer vision tasks with superior performance.
- 3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds81
This work introduces SemanticSTF, an adverse-weather point cloud dataset that provides dense point-level annotations and allows to study 3DSS under various adverse weather conditions, and designs 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 3D semantic segmentation underVarious adverse weather effectively.
- 78
- Scale variance minimization for unsupervised domain adaptation in image segmentation71
A scale variance minimization method that introduces certain supervision in the target domain by imposing a scale-invariance constraint while learning to segment an image and its scale-transformation concurrently and achieves superior domain adaptive segmentation performance as compared with the state-of-the-art.
- Cross-View Regularization for Domain Adaptive Panoptic Segmentation66
This work designs a domain adaptive panoptic segmentation network that exploits inter-style consistency and inter-task regularization for optimal domain adaptivePanoptic segmentsation.
- Box-level segmentation supervised deep neural networks for accurate and real-time multispectral pedestrian detection66
A novel box-level segmentation supervised learning framework for accurate and real-time multispectral pedestrian detection by incorporating features extracted in visible and infrared channels, which outperforms state-of-the-art approaches in terms of both accuracy and speed.
- FPS-Net: A convolutional fusion network for large-scale LiDAR point cloud segmentation64
FPS-Net is designed, a convolutional fusion network that exploits the uniqueness and discrepancy among the projected image channels for optimal point cloud segmentation and achieves superior semantic segmentation as compared with state-of-the-art projection-based methods.
- Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation57
This paper presents an unbiased subclass regularization network (USRN) that alleviates the class imbalance issue by learning class-unbiased segmentation from balanced subclass distributions and designs an entropy-based gate mechanism to coordinate learning between the original classes and the clustered subclasses which facilitates subclassregularization effectively.
- Multi-level adversarial network for domain adaptive semantic segmentation51
A novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally and design a multi- level consistency map that can guide domain adaptation in both input space and output space.
- Domain Adaptive Video Segmentation via Temporal Consistency Regularization47
DA-VSN is presented, a domain adaptive video segmentation network that addresses domain gaps in videos by temporal consistency regularization (TCR) for consecutive frames of target-domain videos.
- Exploiting fusion architectures for multispectral pedestrian detection and segmentation34
A unified mult ispectral fusion framework for joint training of semantic segmentation and target detection that outperforms state-of-the-art multispectral pedestrian detectors by a large margin on the KAIST benchmark dataset is presented.
- Masked Generative Adversarial Networks Are Data-Efficient Generation Learners33
This paper develops two masking strategies that work along orthogonal dimensions of training images, including a shifted spatial masking that masks the images in spatial dimensions with random shifts, and a balanced spectral masker that masks certain image spectral bands with self-adaptive probabilities.
- 30
- Unsupervised Domain Adaptation for Multispectral Pedestrian Detection23
Experimental results show that the proposed unsupervised multimodal domain adaptation method achieves significantly higher detection performance than the approach without domain adaptation, and is competitive with the supervised multispectral pedestrian detectors.
- Zoom-Refine: Boosting High-Resolution Multimodal Understanding via Localized Zoom and Self-Refinement18
Zoom-Refine harnesses the MLLM's inherent capabilities for spatial localization, contextual reasoning and comparative analysis without requiring additional training or external experts to address this issue.
- 17
- 16
- 13
- 13
- 12
- Class-Independent Regularization for Learning with Noisy Labels11
For effective training of CIR, a heterogeneous adaptive co-teaching strategy is designed that forces the class-independent and class-dependent classifiers to focus on sample selection and image classification, respectively, in a cooperative manner.
- 10
- 8
- 5
- 4
- ContextualCoder: Adaptive In-Context Prompting for Programmatic Visual Question Answering3
This paper proposes ContextualCoder, a novel prompting framework tailored for PVQA models that surpasses state-of-the-art models and facilitates the use of diverse in-context information for code generation, thereby improving the performance of PVQA models.
- 2
- 2
- Controllable and Gradual Facial Blemishes Retouching Via Physics-Based Modelling1
The CGFR is based on physical modelling, adopting Sum-of-Gaussians to approximate skin subsurface scattering in a decomposed melanin and haemoglobin color space, and shows that CGFR can realistically simulate the blemishes’ gradual recovering process.
- Multimodal Fusion Architectures for Pedestrian Detection1
A unified multimodal fusion framework for joint training of target detection and segmentation supervision which achieves the state-of-the-art multi-modal pedestrian detection performance on the public KAIST benchmark dataset is presented.
- –
- –
- Rethinking the Evaluation of Visible and Infrared Image Fusion–
A Segmentation-oriented Evaluation Approach (SEA) to assess VIF methods by incorporating the semantic segmentation task and leveraging segmentation labels available in latest VIF datasets, which is hoped will guide the development of novel and practical VIF methods.
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.