@JanisPostels
Joined September 2019
  • Tweets24
  • Following221
  • Followers105
2Media
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 arxiv.org/abs/2107.00649
2
6
2
31
Looking forward to this :)
Bertrand Charpentier
@Bertrand_Charp28 Nov 2022
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). uncertainty-reading-group.gi… Co-author: @JWeissteiner, Hanna Wutte, @SvenSeuken, Josef Teichmann
2
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: arxiv.org/abs/2208.08932

ManiFlow: Implicitly Representing Manifolds with Normalizing Flows

Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constraint imposes...

arxiv.org
1
5
Very happy to announce our workshop on Probabilistic Robotics at #IROS 2022 in Kyoto.  probabilisticrobotics.github… Jointly organized with @FengJianxiang @JongseokLee11 @matthiashumt @YizheWu5 Rudolph Triebel
1
2
16
This WS brings together experts from both fields - probabilistic methods in robotics and deep learning - to provide a forum for this urgent topic. @wolfram_burgard @contactrika @nikoSuenderhauf  Fabio Ramos  Teresa Vidal  @yaringal  Ali Agha  @balajiln  @padsmagt  @IngmarPosner
2
1
5
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. openreview.net/group?id=IROS…)

IROS 2022 Workshop PRDL

Welcome to the OpenReview homepage for IROS 2022 Workshop PRDL

openreview.net
2
1
Janis Postels retweeted
Markus Nagel@mnagel8720 Jul 2022
If your are at #ICML2022, join us Thursday at 11:00 in the Ballroom 1&2 for our oral presentation on "Overcoming Oscillations in Quantization-Aware Training" and later at poster #227. Paper: arxiv.org/abs/2203.11086 @mfournarakis, @yell1337, @TiRune.
1
4
1
13
Would you rather play games or watch random images? In our #ICML2022 work, we give RL agents this choice and turns out many curiosity algos would prefer to watch random images. We propose an acetylcholine-inspired solution to help curiosity to avoid these "noisy TVs"
3
16
4
77
Janis Postels retweeted
Auke Wiggers@aukejw20 Jul 2022
The MobileCodec paper is now online: arxiv.org/abs/2207.08338 Check it out if you want to know how we were able to deploy a neural video codec to a mobile phone and decode 720p video in real time 📲
3
19
3
64
Janis Postels retweeted
Ferjad Naeem@ferjadnaeem19 Jul 2022
I am excited to share that our work "3D Compositional Zero-shot Learning with DeCompositional Consensus" has been accepted at #ECCV2022. Joint work with @evinpinar @xyongqin, Luc Van Gool and @fedassa between ETH Zurich, TUM, and Google. arxiv.org/abs/2111.14673 [1/7]
2
8
1
53
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.
2
Great work guys!
Mattia Segu@MattiaSegu19 Jun 2022
Replying to @CVPR
@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: vis.xyz/shift/ Paper: go.yf.io/shift-paper
4
Janis Postels retweeted
Andrei Bursuc@abursuc4 Jun 2022
Cool new AD dataset in town 👉 SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation by @JanisPostels @MattiaSegu @DrFisherYu @fedassa et al. vis.xyz/shift/ 1/
1
6
28
Glad to share that we will present our work "Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction" tomorrow at 3DV. Paper: arxiv.org/abs/2106.03135 Code: github.com/janisgp/go_with_t… Poster at 11:20am GMT (03.12.)/00:20am GMT (04.12.) >>
2
7
25
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.
1
Janis Postels retweeted
Federico Tombari@fedassa9 Jun 2021
Our work on Variational Transformer Networks for layout generation got featured on the Google AI blog. The work will be presented at CVPR21 on June 24th and a pre-release is available on arXiv. Blog post: Official Tweet: https:/…lnkd.in/dSuZVFx lnkd.in/dBgXeRp

#cvpr2021 #research #ai #google #deeplearning #ml | Federico Tombari

Our work on Variational Transformer Networks for layout generation got featured on the Google AI blog. The work will be presented at CVPR21 on June 24th and a pre-release is available on arXiv. Blog...

linkedin.com
3
18
Janis Postels retweeted
arxiv@arxiv_org9 Dec 2020
Quantifying Aleatoric and Epistemic Uncertainty Using Density Estimation in Latent Space. arxiv.org/abs/2012.03082
2
4
Looking forward to interesting discussions :-)
Federico Tombari@fedassa10 Dec 2020
Our poster on uncertainty estimation for neural networks presented today at the NeurIPS Bayesian DL meetup (poster F13) arxiv.org/abs/2012.03082 bayesiandeeplearning.org/
1
Janis Postels retweeted
Federico Tombari@fedassa6 Jul 2020
Very happy to share that 5 of our papers got accepted at #eccv2020, of which 3 as orals (top 2% this year). Kudos to all my awesome co-authors across Google, TUM, Stanford, Oxford, Chalmers, Tsinghua (among others) for the great work and results. More det…lnkd.in/dZDq8AM
1
9
Load more