Shijian Lu lists you as their PhD student. Claim this profile to confirm it and keep the rest of your record right.
Claim this profileAcademic lineage
View as a treeAdvisors
Works40 from public data
- 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.
- 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 Survey156
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.
- PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds153
PolarMix enriches point cloud distributions and preserves point cloud fidelity via two cross-scan augmentation strategies that cut, edit, and mix point clouds along the scanning direction.
- 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.
- 95
- 93
- 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.
- A Survey of Label-Efficient Deep Learning for 3D Point Clouds70
A taxonomy is proposed that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels, and categorizes four typical label-efficient learning approaches that significantly reduce point cloud annotation efforts: data augmentation, domain transfer learning, weakly-supervised learning, and pretrained foundation models.
- Super-Resolution for “Jilin-1” Satellite Video Imagery via a Convolutional Network68
A five-layer end-to-end network structure without any pre-processing and post-processing, but imposes a reshape or deconvolution layer at the end of the network to retain the distribution of ground objects within the image.
- 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.
- 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.
- An Indoor Positioning System Based on Static Objects in Large Indoor Scenes by Using Smartphone Cameras62
An indoor positioning system to locate users in large indoor scenes by using smartphone cameras and integrating algorithms of deep learning and computer vision that is able to achieve positioning accuracy within 1 m.
- Indoor Visual Positioning Aided by CNN-Based Image Retrieval: Training-Free, 3D Modeling-Free60
A localization method based on image retrieval that can efficiently result in high location accuracy as well as orientation estimation and attempts to use lightweight datum to present the scene.
- 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.
- Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining56
A comprehensive study of CD-FSS is undertaken and reveals the necessity of a fine-tuning stage to effectively transfer the learned meta-knowledge across domains, and the overfitting risk during the naive fine-tuning due to the scarcity of novel category examples is uncovered.
- CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Model51
CAT-SAM is presented, a ConditionAl Tuning network that adapts SAM toward various unconventional target tasks with just few-shot target samples, and two CAT-SAM variants achieve superior target segmentation performance consistently even under the very challenging one-shot adaptation setup.
- 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.
- Bi-level Feature Alignment for Versatile Image Translation and Manipulation34
A versatile image translation and manipulation framework that achieves accurate semantic and style guidance in image generation by explicitly building a correspondence and designs a novel confidence feature injection module which mitigates mismatch problem by fusing features adaptively according to the reliability of built correspondences.
- 30
- 19
- 19
- 17
- 15
- 13
- 8
- PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency6
PacGDC is a label-efficient technique that enhances data diversity with minimal annotation effort for generalizable depth completion, and achieves remarkable generalizability across multiple benchmarks, excelling in diverse scene semantics/scales and depth sparsity/patterns under both zero-shot and few-shot settings.
- 6
- 6
- 6
- Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation5
Concept Curation (CoCu), a pipeline that leverages CLIP to compensate for the missing semantics of visual concepts captured in textual representations, is proposed, suggesting the value of bridging semantic gap in pre-training data.
- 5
- 1
- –
- –
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 2026-10-10. 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. You will be asked to sign in.