Pinned Tweet
📢 We introduce SurgicaL-CD, a diffusion model to generate realistic, labeled surgical images in one step
🎉 I'm excited to share that our work is accepted at the ECCV 2024 workshop on Synthetic Data for Computer Vision
Paper : arxiv.org/abs/2408.09822
1/5🧵
Danush @ ICML ✈️ retweeted
🇪🇺 Big news: This fall, my lab will transition to @tudresden_de. Our affiliations will be with the Department of Surgery at the university hospital and @EKFZdigital, and we will continue our mission to rigorously develop, benchmark, and clinically evaluate #surgicalAI tools.
FID for generative models : If we monitor FID during DM training and expect it to go down over longer training steps, what are we measuring here 🤔
What if the model merely starts to replicate the data from the training set ? This could also lead to lower FID 😉
How to make sure this phenomenon is not happening? Maybe this does not happen at a larger scale ? Happy to hear thoughts from diffusion folks
#diffusionmodels #NeurIPS2025
Danush @ ICML ✈️ retweeted
I’m Shawn, founder of Memories.ai, former researcher at Meta and CS PhD at University of Cambridge.
Today we’re launching Memories.ai: we built the world’s first Large Visual Memory Model - to give AI human-like visual memories.
Why visual memory?
AI to date is chat-based, which has great applications, but humans are not only chat based. Humans have visual-memories, and are visually driven. Memories.ai enables AI agents, softwares, and even robots to see and remember the world the way humans do.
We just raised an $8m seed round led by @susaventures to build the visual-memory layer for AI.
Why is Memories.ai so groundbreaking? 👇
Danush @ ICML ✈️ retweeted
📌🌎🩺🔬🫀
1. The 2025 STIR Challenge (STIRC2025) is launched: synapse.org/Synapse:syn65877… Submit your trackers by Aug. #MICCAI2025 #endovis
2. STIRC2024 paper (and data) released: arxiv.org/abs/2503.24306! Thank you to participants + our sponsors @IntuitiveSurg @ImFusionGmbH @nvidia
Under rated researcher skill:
Sharing the link to the arxiv page and not the pdf. It's annoying when using a phone 😅
Danush @ ICML ✈️ retweeted
For our Robotics at Leeds Seminar Series in January, @SpeidelStefanie will give a talk titled "Beyond the Scalpel: Empowering Surgeons with AI-powered Robotics".
28th Jan, 14:00-15:00
Sir William Henry Bragg GR 25
More info is available at shorturl.at/qA6NP
Danush @ ICML ✈️ retweeted
We kicked off this holiday season with a thrilling escape room adventure, followed by a cosy dinner filled with laughter and good vibes. 🎉
Here’s to teamwork, memories, and an incredible year ahead! 🥂✨@NCT_UCC_DD
Danush @ ICML ✈️ retweeted
Happy to have hosted the visit to @NCT_UCC_DD of schoolgirls from @TactileInternet CeTI #Girlsforrobots. Inspiring lecture by @SpeidelStefanie and amazing Demos showcased the research of computer- and robot-assisted surgery and promoted schoolgirls' interest in scientific fields
Danush @ ICML ✈️ retweeted
#EndoVis24 took place today during #MICCAI2024 in Marrakesh. Thanks to all organizers we had a record number of 8 sub-challenges with diverse applications. Hope to see you all next year for our 10 years anniversary 🎂 @endo_vis @lena_maierhein @DanStoyanov @MICCAI_Society
Danush @ ICML ✈️ retweeted
Thrilled to be attending #MICCAI2024 in the stunning city of Marrakesh! Looking forward to @endo_vis taking place this Thursday! @MICCAI_Society @NCT_UCC_DD #FedSurg #OSS
📌 Our approach shows a 10x inference speed up with improved semantic consistency
📌 Downstream semantic segmentation combining generated and real images leads to 15% improvement
4/5 🧵
Thanks to all the authors!! @DominikRivoir Micha Pfeiffer @SpeidelStefanie
Code : gitlab.com/nct_tso_public…
See you in Milan🇮🇹 !!
@SECAI_School @NCT_UCC_DD
@TSO_Lab @eccvconf
#ECCV2024 #SyntheticData4CV #SurgicalDataScience
📌 Our approach shows a 10x inference speed up with improved semantic consistency
📌 Downstream semantic segmentation combining generated and real images leads to 15% improvement
4/5 🧵
Thanks to all the authors!! @DominikRivoir Micha Pfeiffer @SpeidelStefanie
Code : gitlab.com/nct_tso_public/ga…
See you in Milan🇮🇹 !!
@SECAI_School @NCT_UCC_DD
@TSO_Lab @eccvconf
#ECCV2024 #SyntheticData4CV #SurgicalDataScience