Janis Postels
@JanisPostels
Followers
111
Following
115
Statuses
24
Joined September 2019
Will be presenting our work "On the Practicality of Deterministic Epistemic Uncertainty" next week at #ICML2022 in Baltimore. If you are interested checkout our paper or visit us at our poster on Tue Jul 19 between 06:30 PM & 08:30 PM @ Hall E 506
2
6
30
Looking forward to this :)
Jakob Heiss will present his ICML paper "NOMU - Neural Optimization-based Model Uncertainty" at the Uncertainty in AI reading group today at 5:30pm (Berlin time). Co-author: @JWeissteiner, Hanna Wutte, @SvenSeuken, Josef Teichmann
0
0
1
Will be presenting our work "ManiFlow: Implicitly Representing Manifolds with Normalizing Flows" at #3DV tomorrow! We show how to sample from manifolds (e.g. Point Clouds) with normalizing flows! @MDanelljan Luv Van Gool @fedassa Paper:
1
0
4
@lilianweng Great summary! Would have saved me a lot of time if I'd seen it a little earlier :-D
0
0
0
Further, we invite you to share your recent/ongoing work in this area. There will be a total prize pool of up to 1500$ distributed among the best submissions.
0
2
1
RT @MavorParker: Would you rather play games or watch random images? In our #ICML2022 work, we give RL agents this choice and turns out man…
0
16
0
RT @aukejw: The MobileCodec paper is now online: Check it out if you want to know how we were able to deploy a neu…
0
19
0
RT @ferjadnaeem: I am excited to share that our work "3D Compositional Zero-shot Learning with DeCompositional Consensus" has been accepted…
0
8
0
@abursuc Congrats! Let me know when the preprint is available. Looking forward to that work and seeing you at ECCV!
0
0
1
We shed light onto a recent trend in uncertainty quantification which treats the weights of DNNs deterministically. Turns despite good OOD detection these methods do not necessarily yield well calibrated uncertainty.
0
0
2
Great work guys!
@CVPR time has finally come! Check out our paper "SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation" and drop by our poster session on Friday 24 (afternoon) at 257B to learn more! Project Page: Paper:
0
0
4
RT @abursuc: Cool new AD dataset in town 👉 SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation by @JanisPostels…
0
6
0
Single NFs struggle to model geometries with different geometric properties than the base distribution (e.g. transforming a Gaussian into a ring-shaped distribution) We show that mixtures of NFs are strong inductive bias to overcome this problem in a parameter-efficient way.
0
0
1
RT @fedassa: Our work on Variational Transformer Networks for layout generation got featured on the Google AI blog. The work will be presen…
0
3
0