
Simone Schaub
@schaub_simone
Research group leader @Hessian_AI @TUDarmstadt | Dr. sc. @ETH_en | Computer Vision & Deep Learning
@simoneschaub.bsky.social
ID: 1260606010693222400
https://schaubsi.github.io/ 13-05-2020 16:21:19
56 Tweet
412 Followers
267 Following

Excited to share our GCPR 2025 2024 paper, “DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning” by Tobias Lingenberg, Markus Reuter, Gopika Sudhakaran, Dominik Gojny, Stefan Roth and Simone Schaub! 🎉 #GCPR2024



If you're interested in how different model design choices affect attribution quality, check out our (Simone Schaub and Stefan Roth) paper "Benchmarking the Attribution Quality of Vision Models," which has been accepted at #NeurIPS2024 NeurIPS Conference D&B track!


This year's #ECCV2024 recap: Presented our work w Shashank Agnihotri on Uspampling ⬆️, our work on infinitely large convolutions ♾️ , went to the Doctoral Consortium 🎓 and met with new and old friends 🍻 thanks European Conference on Computer Vision #ECCV2026, it was a blast!


🎓Interested in doing a PhD on interpretability and robustness of AI models in computer vision? I am accepting applications through ELLIS. Application instructions: ellis.eu/news/ellis-phd… Deadline: November 15, 2024, 23:59 CET ELLIS TU Darmstadt Visual Inference Lab

‼️Hiring a permanent #research #scientist in my team CVI2 Research Group in #Luxembourg . If interested apply now! 👉 emea3.mrted.ly/3rvif Questions? DM me! #AI #ComputerVision #PermanentPosition #ResearchOpportunity

Our work, "Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals" is accepted at Transactions on Machine Learning Research!🎉 visinf.github.io/primaps/ PriMaPs generate masks from self-supervised features, enabling to boost unsupervised semantic segmentation via stochastic EM.

Want to learn about how model design choices affect the attribution quality of vision models? Visit our #NeurIPS2024 poster on Friday afternoon (East Exhibition Hall A-C #2910)! Robin Hesse Simone Schaub Stefan Roth Paper: arxiv.org/abs/2407.11910 Code: github.com/visinf/idsds





GLASS: Guided Latent Slot Diffusion for Object-Centric Learning by kris , Simone Schaub, and Stefan Roth Project Page: visinf.github.io/glass Sunday 4:00 PM, ExHall D, Poster 239


Disentangling Polysemantic Channels in Convolutional Neural Networks by Robin Hesse, Jonas Fischer, Simone Schaub, and Stefan Roth Paper: arxiv.org/abs/2504.12939 Talk: Thursday 11:40 AM, Grand ballroom C1 (4th floor) Poster: Thursday, 12:30 PM, ExHall D, Poster 31-60







