Simone Schaub (@schaub_simone) 's Twitter Profile
Simone Schaub

@schaub_simone

Research group leader @Hessian_AI @TUDarmstadt | Dr. sc. @ETH_en | Computer Vision & Deep Learning
@simoneschaub.bsky.social

ID: 1260606010693222400

linkhttps://schaubsi.github.io/ calendar_today13-05-2020 16:21:19

56 Tweet

412 Followers

267 Following

Visual Inference Lab (@visinf) 's Twitter Profile Photo

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

Excited to share our <a href="/gcpr_by_dagm/">GCPR 2025</a> 2024 paper, “DIAGen: Semantically Diverse Image Augmentation with Generative Models for Few-Shot Learning” by Tobias Lingenberg, Markus Reuter, <a href="/gopika_sudhakar/">Gopika Sudhakaran</a>, Dominik Gojny, <a href="/stefanroth/">Stefan Roth</a> and <a href="/schaub_simone/">Simone Schaub</a>! 🎉

#GCPR2024
Simone Schaub (@schaub_simone) 's Twitter Profile Photo

Join us for an interesting afternoon on Sunday at #ECCV2024 with talks, discussions, and poster session on explainability in computer vision. All details: excv-workshop.github.io

Robin Hesse (@robinhesse_) 's Twitter Profile Photo

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!

If you're interested in how different model design choices affect attribution quality, check out our (<a href="/schaub_simone/">Simone Schaub</a> and <a href="/stefanroth/">Stefan Roth</a>) paper "Benchmarking the Attribution Quality of Vision Models," which has been accepted at #NeurIPS2024 <a href="/NeurIPSConf/">NeurIPS Conference</a> D&amp;B track!
Julia Grabinski@ICLR (@juliagrabinski) 's Twitter Profile Photo

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!

This year's #ECCV2024 recap: Presented our work w <a href="/shashankska/">Shashank Agnihotri</a> on Uspampling ⬆️, our work on infinitely large convolutions ♾️ , went to the Doctoral Consortium 🎓 and met with new and old friends 🍻 thanks <a href="/eccvconf/">European Conference on Computer Vision #ECCV2026</a>, it was a blast!
Simone Schaub (@schaub_simone) 's Twitter Profile Photo

🎓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

Djamila Aouada (@aouadadjamila) 's Twitter Profile Photo

‼️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

Visual Inference Lab (@visinf) 's Twitter Profile Photo

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.

Visual Inference Lab (@visinf) 's Twitter Profile Photo

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

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)! <a href="/robinhesse_/">Robin Hesse</a> <a href="/schaub_simone/">Simone Schaub</a> <a href="/stefanroth/">Stefan Roth</a>

Paper: arxiv.org/abs/2407.11910
Code: github.com/visinf/idsds
Martin Mundt (@mundt_martin) 's Twitter Profile Photo

Why has continual ML not had its breakthrough yet? In our new collaborative paper we argue that“Continual Learning Should Move Beyond Incremental Classification”! We highlight 5 examples to illustrate where CL algos can fail & pinpoint 3 key challenges! arxiv.org/abs/2502.11927

Why has continual ML not had its breakthrough yet?

In our new collaborative paper we argue that“Continual Learning Should Move Beyond Incremental Classification”!

We highlight 5 examples to illustrate where CL algos can fail &amp; pinpoint 3 key challenges!

arxiv.org/abs/2502.11927
Dima Damen (@dimadamen) 's Twitter Profile Photo

Supporting #CVPR2025 #CVPR2025 conference organisation as Senior AC gives you an opportunity to meet great colleagues who are similarly volunteering as ACs and lead ACs. I had 10 meetings over 5 days to finalise decisions for 540 in my SAC batch! Here is the evidence! 🧵 of 🖼️

Supporting <a href="/CVPR/">#CVPR2025</a> #CVPR2025 conference organisation as Senior AC gives you an opportunity to meet great colleagues who are similarly volunteering as ACs and lead ACs.  I had 10 meetings over 5 days to finalise decisions for 540 in my SAC batch! Here is the evidence!
🧵 of 🖼️
Laixi Shi (@shilaixi) 's Twitter Profile Photo

🚀 Rising Star Workshops for Junior/Senior PhDs, and Postdocs! 🌟 Don't miss these career-boosting opportunities! notion.so/List-of-Rising… Please share with your peers, students, and anyone who might benefit! #PhD #Postdoc #Academia #RisingStars

🚀 Rising Star Workshops for Junior/Senior PhDs, and Postdocs!

🌟 Don't miss these career-boosting opportunities!
notion.so/List-of-Rising…

Please share with your peers, students, and anyone who might benefit! #PhD #Postdoc #Academia #RisingStars
Visual Inference Lab (@visinf) 's Twitter Profile Photo

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

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning

by <a href="/krissingh_/">kris</a> , <a href="/schaub_simone/">Simone Schaub</a>, and <a href="/stefanroth/">Stefan Roth</a>

Project Page: visinf.github.io/glass

Sunday 4:00 PM, ExHall D, Poster 239
Visual Inference Lab (@visinf) 's Twitter Profile Photo

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

Disentangling Polysemantic Channels in Convolutional Neural Networks

by <a href="/robinhesse_/">Robin Hesse</a>, <a href="/JonasFischerML/">Jonas Fischer</a>, <a href="/schaub_simone/">Simone Schaub</a>, and <a href="/stefanroth/">Stefan Roth</a>

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
Sukrut Rao (@sukrutrao) 's Twitter Profile Photo

Join us in taking stock of the state of the field of explainability in computer vision, at our Workshop on Explainable Computer Vision: Quo Vadis? at #ICCV2025! #ICCV2025 Explainable AI

Join us in taking stock  of the state of the field of explainability in computer vision, at our  Workshop on Explainable Computer Vision: Quo Vadis? at #ICCV2025!

<a href="/ICCVConference/">#ICCV2025</a> <a href="/XAI_Research/">Explainable AI</a>
Robin Hesse (@robinhesse_) 's Twitter Profile Photo

Got a strong XAI paper rejected from ICCV? Submit it to our ICCV eXCV Workshop today—we welcome high-quality work! 🗓️ Submissions open until June 26 AoE. 📄 Got accepted to ICCV? Congrats! Consider our non-proceedings track. #ICCV2025 #ICCV2025

Got a strong XAI paper rejected from ICCV? Submit it to our ICCV eXCV Workshop today—we welcome high-quality work!
🗓️ Submissions open until June 26 AoE.
📄 Got accepted to ICCV? Congrats! Consider our non-proceedings track.
#ICCV2025 <a href="/ICCVConference/">#ICCV2025</a>
Sweta Mahajan (@swetamahajan1) 's Twitter Profile Photo

Introducing the speakers for the eXCV workshop #ICCV2025. Get ready for stimulating and insightful talks and discussions. Our Non-proceedings track is still open! Paper submission deadline: July 18, 2025 More info at: excv-workshop.github.io

Introducing the speakers for the eXCV workshop <a href="/ICCVConference/">#ICCV2025</a>.  Get ready for stimulating and insightful talks and discussions. 

Our Non-proceedings track is still open!

Paper submission deadline: July 18, 2025

More info at: excv-workshop.github.io
Sweta Mahajan (@swetamahajan1) 's Twitter Profile Photo

🚨Deadline Extension Alert! Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV. Our nectar track accepts published papers, as is. More info at: excv-workshop.github.io #ICCV2025 #ICCV2025

🚨Deadline Extension Alert!

Our Non-proceedings track is open till August 15th for the eXCV workshop at ICCV.   

Our nectar track accepts published papers, as is.

More info at: excv-workshop.github.io

<a href="/ICCVConference/">#ICCV2025</a> #ICCV2025
Sukrut Rao (@sukrutrao) 's Twitter Profile Photo

Are you an XAI researcher attending #ICCV2025? Submit your recently published work — at CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI etc. — to the eXCV Workshop for the opportunity to further showcase your work! Published papers can be submitted as is, no rewriting necessary.

Are you an XAI researcher attending #ICCV2025?  Submit your recently published work — at CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, AAAI etc. — to the eXCV Workshop  for the opportunity to further showcase your work! Published papers can be submitted as is, no rewriting necessary.
Visual Inference Lab (@visinf) 's Twitter Profile Photo

Some impressions from our VISINF summer retreat at Lizumer Hütte in the Tirol Alps — including a hike up Geier Mountain and new research ideas at 2,857 m! 🇦🇹🏔️

Some impressions from our VISINF summer retreat at Lizumer Hütte in the Tirol Alps — including a hike up Geier Mountain and new research ideas at 2,857 m! 🇦🇹🏔️