Stefan Roth

papers

1,034

total citations

papers (21)

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

ICCV 2023arXiv

citations

Diverse Image Captioning with Context-Object Split Latent Spaces

NEURIPS 2020arXiv

citations

Dense Unsupervised Learning for Video Segmentation

NEURIPS 2021arXiv

citations

Vision Relation Transformer for Unbiased Scene Graph Generation

ICCV 2023arXiv

citations

Normalizing Flows With Multi-Scale Autoregressive Priors

CVPR 2020arXiv

citations

Probabilistic Pixel-Adaptive Refinement Networks

CVPR 2020arXiv

citations

Adapters Strike Back

CVPR 2024arXiv

citations

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

CVPR 2025arXiv

citations

Scene-Centric Unsupervised Panoptic Segmentation

CVPR 2025arXiv

citations

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

ICCV 2025arXiv

citations

PixelPyramids: Exact Inference Models From Lossless Image Pyramids

ICCV 2021arXiv

citations

Activation Subspaces for Out-of-Distribution Detection

ICCV 2025arXiv

citations

Removing Cost Volumes from Optical Flow Estimators

ICCV 2025arXiv

citations

Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring

CVPR 2021

citations

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

NEURIPS 2020

citations

ART: Adaptive Relation Tuning for Generalized Relation Prediction

ICCV 2025arXiv

citations

Stefan Roth

papers (21)

Single-Stage Semantic Segmentation From Image Labels

Self-Supervised Augmentation Consistency for Adapting Semantic Segmentation

Self-Supervised Monocular Scene Flow Estimation

Self-Supervised Multi-Frame Monocular Scene Flow

Fast Axiomatic Attribution for Neural Networks

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

Diverse Image Captioning with Context-Object Split Latent Spaces

Dense Unsupervised Learning for Video Segmentation

Vision Relation Transformer for Unbiased Scene Graph Generation

Normalizing Flows With Multi-Scale Autoregressive Priors

Probabilistic Pixel-Adaptive Refinement Networks

Adapters Strike Back

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

Scene-Centric Unsupervised Panoptic Segmentation

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

PixelPyramids: Exact Inference Models From Lossless Image Pyramids

Activation Subspaces for Out-of-Distribution Detection

Removing Cost Volumes from Optical Flow Estimators

Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

ART: Adaptive Relation Tuning for Generalized Relation Prediction

papers (21)

Single-Stage Semantic Segmentation From Image Labels

Self-Supervised Augmentation Consistency for Adapting Semantic Segmentation

Self-Supervised Monocular Scene Flow Estimation

Self-Supervised Multi-Frame Monocular Scene Flow

Fast Axiomatic Attribution for Neural Networks

FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods

Diverse Image Captioning with Context-Object Split Latent Spaces

Dense Unsupervised Learning for Video Segmentation

Vision Relation Transformer for Unbiased Scene Graph Generation

Normalizing Flows With Multi-Scale Autoregressive Priors

Probabilistic Pixel-Adaptive Refinement Networks

Adapters Strike Back

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

Scene-Centric Unsupervised Panoptic Segmentation

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

PixelPyramids: Exact Inference Models From Lossless Image Pyramids

Activation Subspaces for Out-of-Distribution Detection

Removing Cost Volumes from Optical Flow Estimators

Learning Spatially-Variant MAP Models for Non-Blind Image Deblurring

Deep Wiener Deconvolution: Wiener Meets Deep Learning for Image Deblurring

ART: Adaptive Relation Tuning for Generalized Relation Prediction