Xiaofei He

papers

1,085

total citations

papers (14)

CLRNet: Cross Layer Refinement Network for Lane Detection

CVPR 2022arXiv

268

citations

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

CVPR 2023arXiv

189

citations

Do Wider Neural Networks Really Help Adversarial Robustness?

NEURIPS 2021arXiv

105

citations

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

ECCV 2022arXiv

citations

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

ECCV 2024arXiv

citations

MLSLT: Towards Multilingual Sign Language Translation

CVPR 2022

citations

Xiaofei He

papers (14)

CLRNet: Cross Layer Refinement Network for Lane Detection

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Do Wider Neural Networks Really Help Adversarial Robustness?

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

Learning To Affiliate: Mutual Centralized Learning for Few-Shot Classification

Depth Any Video with Scalable Synthetic Data

Towards Efficient Adversarial Training on Vision Transformers

Salient Object Ranking With Position-Preserved Attention

Local Conditional Controlling for Text-to-Image Diffusion Models

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

MLSLT: Towards Multilingual Sign Language Translation

papers (14)

CLRNet: Cross Layer Refinement Network for Lane Detection

CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation

Do Wider Neural Networks Really Help Adversarial Robustness?

Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph

GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds

UniPAD: A Universal Pre-training Paradigm for Autonomous Driving

PVT-SSD: Single-Stage 3D Object Detector With Point-Voxel Transformer

Learning To Affiliate: Mutual Centralized Learning for Few-Shot Classification

Depth Any Video with Scalable Synthetic Data

Towards Efficient Adversarial Training on Vision Transformers

Salient Object Ranking With Position-Preserved Attention

Local Conditional Controlling for Text-to-Image Diffusion Models

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts

MLSLT: Towards Multilingual Sign Language Translation