Samuel Schulter

papers

828

total citations

papers (22)

Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

CVPR 2023arXiv

citations

Taming Self-Training for Open-Vocabulary Object Detection

CVPR 2024arXiv

citations

Single-Stream Multi-level Alignment for Vision-Language Pretraining

ECCV 2022arXiv

citations

Understanding Road Layout From Videos as a Whole

CVPR 2020arXiv

citations

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

CVPR 2024arXiv

citations

Exploring Question Decomposition for Zero-Shot VQA

NEURIPS 2023arXiv

citations

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

ICCV 2023arXiv

citations

Generating Enhanced Negatives for Training Language-Based Object Detectors

CVPR 2024arXiv

citations

Efficient Controllable Multi-Task Architectures

ICCV 2023arXiv

citations

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving

NEURIPS 2025arXiv

citations

GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection

CVPR 2025arXiv

citations

LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

CVPR 2025arXiv

citations

Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations

CVPR 2020

citations

Samuel Schulter

papers (22)

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Shuffle and Attend: Video Domain Adaptation

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Domain Adaptive Semantic Segmentation Using Weak Labels

Object Detection with a Unified Label Space from Multiple Datasets

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Controllable Dynamic Multi-Task Architectures

AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving

NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization

Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Taming Self-Training for Open-Vocabulary Object Detection

Single-Stream Multi-level Alignment for Vision-Language Pretraining

Understanding Road Layout From Videos as a Whole

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

Exploring Question Decomposition for Zero-Shot VQA

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Generating Enhanced Negatives for Training Language-Based Object Detectors

Efficient Controllable Multi-Task Architectures

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving

GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection

LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations

papers (22)

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

Shuffle and Attend: Video Domain Adaptation

MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation

Domain Adaptive Semantic Segmentation Using Weak Labels

Object Detection with a Unified Label Space from Multiple Datasets

On Generalizing Beyond Domains in Cross-Domain Continual Learning

Controllable Dynamic Multi-Task Architectures

AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving

NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization

Q: How To Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!

Taming Self-Training for Open-Vocabulary Object Detection

Single-Stream Multi-level Alignment for Vision-Language Pretraining

Understanding Road Layout From Videos as a Whole

Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement

Exploring Question Decomposition for Zero-Shot VQA

OmniLabel: A Challenging Benchmark for Language-Based Object Detection

Generating Enhanced Negatives for Training Language-Based Object Detectors

Efficient Controllable Multi-Task Architectures

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving

GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection

LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations