Margret Keuper

AIM: Amending Inherent Interpretability via Self-Supervised Masking ICCV 2025 Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation ACL 2025 Can We Talk Models Into Seeing the World Differently? ICLR 2025 DCBM: Data-Efficient Visual Concept Bottleneck Models ICML 2025 FAIR-TAT: Improving Model Fairness using Targeted Adversarial Training WACV 2025 I Spy with My Little Eye A Minimum Cost Multicut Investigation of Dataset Frames WACV 2025 TikZero: Zero-Shot Text-Guided Graphics Program Synthesis ICCV 2025 VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis ICLR 2025 Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive ICLR 2024 CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasks ICML 2024 Implicit Representations for Constrained Image Segmentation ICML 2024 Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context ECCV 2024 MultiMax: Sparse and Multi-Modal Attention Learning ICML 2024 Intra-Source Style Augmentation for Improved Domain Generalization WACV 2023 Neural Architecture Design and Robustness: A Dataset ICLR 2023 FrequencyLowCut Pooling – Plug & Play against Catastrophic Overfitting ECCV 2022 Learning Where to Look – Generative NAS Is Surprisingly Efficient ECCV 2022 Robust Models are less Over-Confident NeurIPS 2022 Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks ICLR 2022 Trading off Image Quality for Robustness is not Necessary with Regularized Deterministic Autoencoders NeurIPS 2022 Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis IJCAI 2021 Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation ICCV 2021 Shape your Space: A Gaussian Mixture Regularization Approach to Deterministic Autoencoders NeurIPS 2021 Spectral Distribution Aware Image Generation AAAI 2021 Uncertainty in minimum cost multicuts for image and motion segmentation UAI 2021 Watch Your Up-Convolution: CNN Based Generative Deep Neural Networks Are Failing to Reproduce Spectral Distributions CVPR 2020 Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation ECCV 2018 FlowNet 2.0: Evolution of Optical Flow Estimation With Deep Networks CVPR 2017 Higher-Order Minimum Cost Lifted Multicuts for Motion Segmentation ICCV 2017 ProbFlow: Joint Optical Flow and Uncertainty Estimation ICCV 2017 STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling CVPR 2017 Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts ICCV 2015 Motion Trajectory Segmentation via Minimum Cost Multicuts ICCV 2015 Spectral Graph Reduction for Efficient Image and Streaming Video Segmentation CVPR 2014 Blind Deconvolution of Widefield Fluorescence Microscopic Data by Regularization of the Optical Transfer Function (OTF) CVPR 2013