Christoffer Löffler

Associate Professor at @pucv_cl. Alumni from @FAU_MaD_Lab and @FraunhoferIIS
I'm here for CompSci/AI. @🇩🇪🇨🇱

[Christoffer Löffler @ChristofferLoe1]

In our work on Active Learning of Ordinal Embeddings¹ we joined forces with GaTech's SIPLab to improve the search on trajectory data² with the InfoTuple Active Learning method³
¹ https://t.co/CCA3XR9n8Q
² https://t.co/KMzv0dkcE3
³ https://t.co/Uts9jry6G5

[Christoffer Löffler @ChristofferLoe1]

Our user study on Active Learning of ordinal embeddings got published in @TmlrOrg! See our video at https://t.co/iLRLKB5SSQ for the full story of how we learn similarity functions for football tracking data.
@chris_mutschler @BjoernEskofier @crozSciTech @dariozanca

[Accepted papers at TMLR @TmlrPub]

Active Learning of Ordinal Embeddings: A User Study on Football Data

Christoffer Löffler, Kion Fallah, Stefano Fenu et al..

Action editor: Purnamrita Sarkar.

https://t.co/tMvF471Dvo

#retrievals #retrieval #similarity

[Christopher Mutschler @chris_mutschler]

I am very happy that our paper finally made it into TMLR! @ChristofferLoe1

[Christoffer Löffler @ChristofferLoe1]

Transformers are eating continual learning (datasets)! #NeurIPS2022 workshop by Paul Janson, Wenxuan Zhang, Rahaf Aljundi and @moElhoseiny

[Christoffer Löffler @ChristofferLoe1]

Probably the winner for most creative poster at #NeurIPS2022 used 8 iPads to bring the point across

[Christoffer Löffler @ChristofferLoe1]

@chris_mutschler We’ll have gingerbread for the first six visitors who want to learn about our method for deep active learning. High resolution poster: https://t.co/hg6eBngKr5

[Christoffer Löffler @ChristofferLoe1]

Visit us today at 11am at poster #1008 at #NeurIPS2022. We’ll present our work on Deep Active Learning. For convenience, just start your poster session hiking trip at the end of the hall. @chris_mutschler
https://t.co/EZyTWny4hN

[Christoffer Löffler @ChristofferLoe1]

#pelicansgameday with @chris_mutschler

[Christoffer Löffler @ChristofferLoe1]

Check out our new preprint on active learning for ordinal embeddings: https://t.co/v4kW0MzocV We've collaborated with our friends at SIPLab (Georgia Tech) to learn similarity from few annotations.

[Christoffer Löffler @ChristofferLoe1]

Enjoying our company excursion to volleyball fields on a sunny day with my colleagues from @FraunhoferIIS. Playing a serious fun tournament!

[Christopher Mutschler @chris_mutschler]

Our paper "IALE: Imitating Active Learner Ensembles" is now available on JMLR! 😀 Check it out! @ChristofferLoe1

https://t.co/z0ccqlaV1O

[Christoffer Löffler @ChristofferLoe1]

We've recently benchmarked eight saliency methods for conv. networks on time-series classification and segmentation. Turns out, there is no winner for all combinations of {model, metric, dataset}. Preprint: https://t.co/TnGYbmGsRm Code: https://t.co/tSa2H9u30o #xai #saliency

[Christoffer Löffler @ChristofferLoe1]

I can totally recommend reading Luca's article on Searching for Soccer Scenes using Siamese Neural Networks (in @TDataScience) https://t.co/SWZNiOdGos

[Christopher Mutschler @chris_mutschler]

"I am writing regarding your JMLR manuscript entitled "...."
I am pleased to inform you that your manuscript has been accepted for publication."

Feels really good 😎

@ChristofferLoe1 @JmlrOrg

[Christoffer Löffler @ChristofferLoe1]

I am happy to visit @crozSciTech's SIPLab at @GeorgiaTech for an exciting research collaboration in the coming months. This environment is highly conducive to ideas! #FraunhoferIIS #ADA #FAU

[Christoffer Löffler @ChristofferLoe1]

Our paper on accelerating similarity-based queries for soccer was just published in the ACM Transactions on Intelligent Systems and Technology! Is metric learning your thing? Got trajectory data? Like soccer? This is for you! https://t.co/KMzv0dkcE3

[Christoffer Löffler @ChristofferLoe1]

A short summary / interesting read of Kaparthy’s talking points from CVPR’21 on “why self-driving cars don’t need lidar” (via VentureBeat) https://t.co/JSwIGy5zhb

[Christoffer Löffler @ChristofferLoe1]

TIL: In a distributed ML setting, noise in a communication channel (i.e., between split network layers that run inferences) could be simply interpreted as Gaussian dropout! Thanks for the inspiration @s_scardapane

[Christoffer Löffler @ChristofferLoe1]

Lilian Wang @lilianweng asked "Are Deep Neural Networks Dramatically Overfitted?" and touches many fundamentals, from Occam's Razor over Universal Approx. Theorem to Intrinsic Dimensions and the Lottery Ticket Hypothesis. Lil'Log is always worth reading! https://t.co/6H7zA9N3rn