Computer Vision Freiburg

Lead by Prof. Thomas Brox since 2010

[David Hoffmann @DavidTHoffmann]

@SimonSchrodi and I will present our joint work, “Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models,” this Thursday as an Oral (top 1.8%) at #ICLR2025!🎉
🧵

[Computer Vision Freiburg @CVisionFreiburg]

We are now also on @bluesky. If you're there too, you can follow us: https://t.co/WEIOr7qKDV

[María A. Bravo @MariaAleBravo]

Excited to share that our paper, "Open-Ended VQA Benchmarking of Vision-Language Models by Exploiting Classification Datasets and Their Semantic Hierarchy," has been selected as a Spotlight at #ICLR2024! #AI #VLMs
Paper: https://t.co/THV7DtHOTs
Code: https://t.co/T78xHXhPP9
1/n

[Simon Schrodi @SimonSchrodi]

Excited to present “Climate-sensitive Urban Planning through Optimization of Tree Placements” w/ Ferdinand Briegel, Max Argus, @envmet & @ThomasBrox at the #NeurIPS2023 @ClimateChangeAI workshop. Tl;dr: we optimize urban tree locations for improved outdoor human thermal comfort.

[Simon Schrodi @SimonSchrodi]

#NAS has seen 1000+ papers over the last few years but rarely found new architectures.

In our #NeurIPS2023 paper w/ @DannyStollAI, Robin Ru, @RheaSukthanker, @ThomasBrox & @FrankRHutter, we take a step in that direction and find signs to move beyond usual search spaces!

A 🧵1/n

[María A. Bravo @MariaAleBravo]

Very excited to share our OVAD paper accepted at #CVPR2023 !!!

We introduce an Open-vocabulary Attribute Detection (OVAD) task and the corresponding OVAD benchmark.

Check out the webpage: https://t.co/DXiof1rPfk
1/6

[Philipp Schröppel @PhilSchroeppel]

Happy to announce the 𝗥𝗼𝗯𝘂𝘀𝘁 𝗠𝘂𝗹𝘁𝗶-𝘃𝗶𝗲𝘄 𝗗𝗲𝗽𝘁𝗵 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 #3dv2022.

It evaluates robust depth estimation in an open world setting. Code is available for an easy evaluation of your model!

Paper: https://t.co/Rx2P7o7266
Code: https://t.co/5gJFU21k77
1/N

[Simon Schrodi @SimonSchrodi]

Come check out our poster on June 22 from 2:30-5:00 pm at poster session 2.2, 95b, and have a chat about the paper!

Do you already want to get a sneak peek or cannot attend #CVPR2022? Here's a brief overview: https://t.co/KW3KsR9n1H

[Simon Schrodi @SimonSchrodi]

Excited that our (updated) paper got accepted to #CVPR2022! My first paper to an international conference!
Thanks to my supervisors @t_saikia @ThomasBrox for their great advice and support!

[Computer Vision Freiburg @CVisionFreiburg]

We can also provide lab space to PhD students.

[Computer Vision Freiburg @CVisionFreiburg]

The Computer Vision Group at the University Freiburg offers hosting computer vision researchers from Ukraine with a doctoral degree under the Philipp Schwartz program of the Humboldt Foundation. If you know someone interested to join our team contact Prof. Thomas Brox. #Ukraine

[Computer Vision Freiburg @CVisionFreiburg]

#ScienceForUkraine @Sci_for_Ukraine

[David Hoffmann @DavidTHoffmann]

Today @BehrmannNadine and I present our work "Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives" at #AAAI2022. If you are interested in contrastive learning, representation learning, OOD or ranking visit our poster in poster session 10.

[Computer Vision Freiburg @CVisionFreiburg]

Ever wondered what to do with ambiguous samples in contrastive learning? Check out the recent #AAAI2022 paper "Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives" from @DavidTHoffmann and @BehrmannNadine! https://t.co/EvlV7MVRB9

[osama makansi @_os1a]

Excited to share that our paper "You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction" got accepted to #iclr2022. More details to follow...

[Computer Vision Freiburg @CVisionFreiburg]

Hello World!