Shiliang Pu

papers

1,554

total citations

papers (28)

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

ICCV 2021arXiv

329

citations

Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains

CVPR 2023arXiv

citations

FBNet: Feedback Network for Point Cloud Completion

ECCV 2022arXiv

citations

Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression

CVPR 2022arXiv

citations

Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation

CVPR 2023arXiv

citations

Slimmable Domain Adaptation

CVPR 2022arXiv

citations

Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

AAAI 2024arXiv

citations

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

ECCV 2022arXiv

citations

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

ICCV 2023

citations

RangeIoUDet: Range Image Based Real-Time 3D Object Detector Optimized by Intersection Over Union

CVPR 2021

citations

Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization

CVPR 2023

citations

STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data

NEURIPS 2021

citations

PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification

CVPR 2023

citations

FAM: Visual Explanations for the Feature Representations From Deep Convolutional Networks

CVPR 2022

citations

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

ICCV 2021

citations

Towards Comprehensive Representation Enhancement in Semantics-Guided Self-Supervised Monocular Depth Estimation

ECCV 2022

citations

Enhancing Multi-modal Features Using Local Self-Attention for 3D Object Detection

ECCV 2022

citations

"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

NEURIPS 2022

citations

SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization

NEURIPS 2022

citations

Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly Detection

ICCV 2021

citations

Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection

ICCV 2023

citations

Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds

ICCV 2023

citations

Shiliang Pu

papers (28)

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

Counterfactual Samples Synthesizing for Robust Visual Question Answering

Forward Compatible Few-Shot Class-Incremental Learning

Learning Open Set Network with Discriminative Reciprocal Points

Label Matching Semi-Supervised Object Detection

TransForensics: Image Forgery Localization With Dense Self-Attention

Attention Diversification for Domain Generalization

Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains

FBNet: Feedback Network for Point Cloud Completion

Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression

Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation

Slimmable Domain Adaptation

Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

RangeIoUDet: Range Image Based Real-Time 3D Object Detector Optimized by Intersection Over Union

Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization

STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data

PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification

FAM: Visual Explanations for the Feature Representations From Deep Convolutional Networks

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

Towards Comprehensive Representation Enhancement in Semantics-Guided Self-Supervised Monocular Depth Estimation

Enhancing Multi-modal Features Using Local Self-Attention for 3D Object Detection

"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization

Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly Detection

Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection

Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds

papers (28)

RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation

Counterfactual Samples Synthesizing for Robust Visual Question Answering

Forward Compatible Few-Shot Class-Incremental Learning

Learning Open Set Network with Discriminative Reciprocal Points

Label Matching Semi-Supervised Object Detection

TransForensics: Image Forgery Localization With Dense Self-Attention

Attention Diversification for Domain Generalization

Multi-View Adversarial Discriminator: Mine the Non-Causal Factors for Object Detection in Unseen Domains

FBNet: Feedback Network for Point Cloud Completion

Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression

Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation

Slimmable Domain Adaptation

Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation

RangeIoUDet: Range Image Based Real-Time 3D Object Detector Optimized by Intersection Over Union

Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization

STEP: Out-of-Distribution Detection in the Presence of Limited In-Distribution Labeled Data

PHA: Patch-Wise High-Frequency Augmentation for Transformer-Based Person Re-Identification

FAM: Visual Explanations for the Feature Representations From Deep Convolutional Networks

SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix

Towards Comprehensive Representation Enhancement in Semantics-Guided Self-Supervised Monocular Depth Estimation

Enhancing Multi-modal Features Using Local Self-Attention for 3D Object Detection

"Lossless" Compression of Deep Neural Networks: A High-dimensional Neural Tangent Kernel Approach

SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization

Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly Detection

Distilling DETR with Visual-Linguistic Knowledge for Open-Vocabulary Object Detection

Clusterformer: Cluster-based Transformer for 3D Object Detection in Point Clouds