Andrei Bursuc

papers

1,041

total citations

papers (18)

RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving

CVPR 2023arXiv

118

citations

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

CVPR 2021arXiv

citations

PODA: Prompt-driven Zero-shot Domain Adaptation

ICCV 2023arXiv

citations

TRADI: Tracking Deep Neural network Weight Distributions

ECCV 2020arXiv

citations

Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic Segmentation

ICCV 2021arXiv

citations

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

NEURIPS 2023arXiv

citations

Three Pillars Improving Vision Foundation Model Distillation for Lidar

CVPR 2024arXiv

citations

A Simple Recipe for Language-guided Domain Generalized Segmentation

CVPR 2024arXiv

citations

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

ECCV 2022arXiv

citations

Active Learning Strategies for Weakly-Supervised Object Detection

ECCV 2022arXiv

citations

Latent Discriminant Deterministic Uncertainty

ECCV 2022arXiv

citations

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

CVPR 2024arXiv

citations

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

ICLR 2025arXiv

citations

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

ICCV 2025arXiv

citations

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

ICCV 2025arXiv

citations

Andrei Bursuc

papers (18)

Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data

What to Hide from Your Students: Attention-Guided Masked Image Modeling

Learning Representations by Predicting Bags of Visual Words

RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

PODA: Prompt-driven Zero-shot Domain Adaptation

TRADI: Tracking Deep Neural network Weight Distributions

Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic Segmentation

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

Three Pillars Improving Vision Foundation Model Distillation for Lidar

A Simple Recipe for Language-guided Domain Generalized Segmentation

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

Active Learning Strategies for Weakly-Supervised Object Detection

Latent Discriminant Deterministic Uncertainty

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation

papers (18)

Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data

What to Hide from Your Students: Attention-Guided Masked Image Modeling

Learning Representations by Predicting Bags of Visual Words

RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

PODA: Prompt-driven Zero-shot Domain Adaptation

TRADI: Tracking Deep Neural network Weight Distributions

Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic Segmentation

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

Three Pillars Improving Vision Foundation Model Distillation for Lidar

A Simple Recipe for Language-guided Domain Generalized Segmentation

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation

Active Learning Strategies for Weakly-Supervised Object Detection

Latent Discriminant Deterministic Uncertainty

Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models

MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation