building polybot, a flexible robot for a sustainable agriculture future
Tübingen, Deutschland
Joined April 2010
- Tweets181
- Following629
- Followers398
- Likes2K
Blows my mind that our POLYBOT made it into the opening of #COP27 🤯
Yeah! Our work on an intelligent #robot for #sustainable #farming (POLYBOT) made it into the opening of #COP27 World Leader Summit in the talk of @VeronikaEyring. Interested in bold climate tech solutions? Talk to me or @clmich at #COP27 or DM us.@Cyber_Valley @MPI_IS @ml4science
Claudio Michaelis retweeted
Are you into cutting-edge #HPC/#AI clusters? The Tübingen AI Center, one of Europe's top #ML research institutions, searches for a senior expert to lead its #AI cluster (> 1000 GPUs, > 200 users) team and design an upcoming large-scale upgrade:
cyber-valley.de/en/jobs/head…
Claudio Michaelis retweeted
Are you interested in the generalization capabilities of ImageNet classifiers?
Then attend our workshop! Join us at the ShiftHappens Workshop @icmlconf #ICML2022 this Friday (22 July) 9am - 7:15 pm EST in Ballroom 4!🎉
shift-happens-benchmark.gith… 🧵[1/3]
Come work with us on #robotics for #sustainable agriculture! 🤖🌱
Just started a group at Max Planck Institute for Intelligent Systems (@MPI_IS) & Tübingen AI Center🎉 Focus: robustness, identifiable representation learning & interpretability. Plus a cool project on #AI, #robotics & #sustainable food production. Interested in a #postdoc? DM me!
Claudio Michaelis retweeted
Contribute datasets📷, metrics📊 and tasks🦾 to a community-built, open source benchmark for computer vision models: Submission for the workshop extended until May 27! *Register your abstract until May 17.*
🔗Details: shift-happens-benchmark.gith…
🚀Submission: openreview.net/group?id=ICML…
ALT More details: https://shift-happens-benchmark.github.io/. Abstract Submission May 17, Full submission May 27, Camera Ready July 1, Workshop Date July 22
Claudio Michaelis retweeted
#CaCTüS offers a paid 3-months research #internship in Tübingen open to students who fled Ukraine 🇺🇦 and are now in Germany 🇩🇪 . The project requires some programming experience and interest in data analysis & the brain. More: cactus-internship.tuebingen.…
#ScienceForUkraine
Claudio Michaelis retweeted
📣Part 1 of our quest to better understand the brain was @DeepLabCut.
🔥🦓Now Part 2: Introducing #CEBRA to jointly model neural dynamics & behavior with self-supervised learning. Hypothesis- or data-driven, highly consistent, decodable neural latents
arxiv.org/abs/2204.00673
🧵👇
Claudio Michaelis retweeted
We are thrilled to announce the ShiftHappens Workshop at #icml2022 @icmlconf in which the community builds a challenging open-source benchmark suite for ImageNet-scale models! All accepted submissions will be part of the open-source benchmark suite. [1/6] shift-happens-benchmark.gith…
Claudio Michaelis retweeted
In 2015, ResNets reportedly surpassed human-level performance on #ImageNet. However, a large generalisation gap remained. Which of today’s exciting directions will close the gap: Vision transformers? CLIP? Self-supervised learning? Bigger datasets? Adversarial training? [1/N]
Claudio Michaelis retweeted
I‘m struck that it still hasn’t sunk in how much #b117 may change the course of this pandemic.
The initial shock about it being more transmissible seems to have worn off. But we are barely beginning to see its real-world impact.
A story: sciencemag.org/news/2021/02/…
And a thread
Claudio Michaelis retweeted
love this intro 😂
More classes is all you need for one-shot object detection.
It turns out we can almost close the gap between the detection of known and novel objects simply by increasing the number of categories.
arxiv.org/abs/2011.04267 @clmich @alxecker @MatthiasBethge
[1/7]
Claudio Michaelis retweeted
A bit late to the party but the « Shortcut Learning » paper by R. Geirhos @jh_jacobsen @clmich R. Zemel @wielandbr, @MatthiasBethge & F. Wichmann was a really enjoyable read!
A nice overview connecting NNet failures, OOD robustness, fairness, bias
Here: arxiv.org/abs/2004.07780
Claudio Michaelis retweeted
Check out our new paper Flexible Few-Shot Learning -- the same object can belong to different classes depending on context. We found unsupervised representation is better than supervised. A short version at NeurIPS metalearn workshop today at 10 EST. arxiv.org/abs/2012.05895
Claudio Michaelis retweeted
Introducing the embedding space you didn't know you needed: Human similarity judgments for the entire ImageNet (50k images) validation set. Perfect for evaluating representations, including unsupervised models. It's already bearing fruit, w @BDRoads arxiv.org/abs/2011.11015 (1/3)
Claudio Michaelis retweeted
A close look at what happens when deep learning fails reveals an effect of ‘shortcut learning’. Recognizing that this may be a common characteristic of learning systems, artificial and biological, may help making deep learning more robust. Read the paper: go.nature.com/3lr0GwU
Claudio Michaelis retweeted
Pleased to share that our paper "Shortcut learning in deep neural networks" has been published as a @nature Machine Intelligence Perspective:
nature.com/articles/s42256-0…
PDF access without paywall: rdcu.be/canVv
More classes is all you need for one-shot object detection.
It turns out we can almost close the gap between the detection of known and novel objects simply by increasing the number of categories.
arxiv.org/abs/2011.04267 @clmich @alxecker @MatthiasBethge
[1/7]
Results generally look good even in complex or crowded scenes. While some problems like the high false positive rate (right column) remain, we are confident that our insights will make solving these issues easier as well.
[6/7]
