Mischa Dombrowski

[Mischa Dombrowski @DombrowskiMN]

Thrilled to announce that this week, I had the fantastic opportunity to present our paper 'Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability' as an oral presentation at @RealAAAI as part of the main conference - Safe, Robust, and Responsible AI Track

[Hadrien Reynaud @reynaud_h]

🚨Our latest work on data generation, privacy preservation and surrogate datasets has been (early-)accepted at #MICCAI24 !
And the generation process 120x faster than last year ! 🚀

🌟EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing 🌟

[Johanna P Mueller @Hanna_Paulaluap]

🚀🩻 Exciting collaboration alert! The IDEA Lab @aibe_fau @UniFAU and pediatric specialists at University Hospital Erlangen (#UKER) joined forces to develop a new AI tool for assessing Fontan circulation complications in children with CHD. 🏥🖥️
@BorderlessSci @BernhardKainz1

[Mischa Dombrowski @DombrowskiMN]

If you want the technical details, check out our preprint https://t.co/fiFU1IhDfH.

Thank you, @reynaud_h, @Hanna_Paulaluap, @MertBTwit, and @BernhardKainz1, for your fantastic support.

[Mischa Dombrowski @DombrowskiMN]

Thrilled to announce that this week, I had the fantastic opportunity to present our paper 'Trade-offs in Fine-tuned Diffusion Models Between Accuracy and Interpretability' as an oral presentation at @RealAAAI as part of the main conference - Safe, Robust, and Responsible AI Track

[Mischa Dombrowski @DombrowskiMN]

To train interpretable text-to-image diffusion models, we find three main design principles that you should follow:
1. Keep the language encoder frozen
2. Keep the variability of your input text high
3. Minimize the domain gap

[Mischa Dombrowski @DombrowskiMN]

@anki_xyz How many views do you usually get on recorded lectures?

[Bernhard Kainz @BernhardKainz1]

Self-supervised single-class strategies with histogram-equalised gradient upscaling are showing promise. @Hanna_Paulaluap ‘s approach surpasses existing benchmarks. 🧠🔍
#MICCAI23 UNSURE
https://t.co/xIs9JcwbmK
@aibe_fau @BioMedIAICL @BorderlessSci #MICCAI2023

[Andreas K. Maier @maier_ak]

The @unifau team at #MICCAI2023!

cc @MICCAI_Society @MiccaiStudents

[Bernhard Kainz @BernhardKainz1]

The 4th International Workshop of Advances in Simplifying Medical UltraSound (ASMUS) - a workshop held in conjunction with #MICCAI23 is only a few days away. Join us on
Sunday 8⃣ Oct
from 8⃣ AM in
Meeting Room 8⃣
Vancouver Convention Center East Building Level 1.

[Johanna P Mueller @Hanna_Paulaluap]

🔎 We've developed an improved self-supervised single-class training strategy that approximates probabilistic inference with loosen feature locality constraints. Our approach with Probabilistic Poisson Image Interpolation (P-PII) shows promise in identifying unknown unknowns.

[Mischa Dombrowski @DombrowskiMN]

Special thanks to my fantastic co-authors @reynaud_h, @MertBTwit, and my supervisor @BernhardKainz1.

[Mischa Dombrowski @DombrowskiMN]

Excited to go to #ICCV2023 next week, where I will present our work on "Foreground-Background Separation through Concept Distillation from Generative Image Foundation Models" during the poster session on Wednesday at 10:30 a.m. https://t.co/CeWo2kmeyj

[Mischa Dombrowski @DombrowskiMN]

If you are interested in how we leverage pre-trained diffusion models to teach them concepts like foreground and background, come visit me for some exciting discussions.

[Mischa Dombrowski @DombrowskiMN]

@ICCVConference, do you know when you will release some information about the virtual poster and video presentation submission?

[Bernhard Kainz @BernhardKainz1]

I am looking for a PhD student to be hosted in Germany @BorderlessSci, co-funded and co-located with industry. PM/email in case of interest (please attach your CV)

[Bernhard Kainz @BernhardKainz1]

Due to numerous requests will the paper submission deadline for ASMUS 2023 be extended to 10 July 2023.

[Bernhard Kainz @BernhardKainz1]

📢fully-funded PhD/PostDoc position in my group. Many opportunities for making progress in self-supervised learning for medical image analysis and beyond. Details of positions and how to apply here: https://t.co/jHQml19URC