40 citations · 74 across the 18 of their papers we have counts for
18 papers
Uncertainty Quantification via Stable Distribution Propagation
Felix Petersen, Aashwin Mishra, Hilde Kuehne +3
We propose a new approach for propagating stable probability distributions through neural networks. Our method is based on local linearization, which we show to be an optimal appro…
Grounding Everything: Emerging Localization Properties in Vision-Language Transformers
Walid Bousselham, Felix Petersen, Vittorio Ferrari +1
Vision-language foundation models have shown remarkable performance in various zero-shot settings such as image retrieval, classification, or captioning. But so far, those models s…
Neural Machine Translation for Mathematical Formulae
Felix Petersen, Moritz Schubotz, Andre Greiner-Petter +1
We tackle the problem of neural machine translation of mathematical formulae between ambiguous presentation languages and unambiguous content languages. Compared to neural machine…
ISAAC Newton: Input-based Approximate Curvature for Newton's Method
Felix Petersen, Tobias Sutter, Christian Borgelt +4
We present ISAAC (Input-baSed ApproximAte Curvature), a novel method that conditions the gradient using selected second-order information and has an asymptotically vanishing comput…
Learning by Sorting: Self-supervised Learning with Group Ordering Constraints
Nina Shvetsova, Felix Petersen, Anna Kukleva +2
Contrastive learning has become an important tool in learning representations from unlabeled data mainly relying on the idea of minimizing distance between positive data pairs, e.g…
Deep Differentiable Logic Gate Networks
Felix Petersen, Christian Borgelt, Hilde Kuehne +1
Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learnin…
Learning with Differentiable Algorithms
Felix Petersen
Classic algorithms and machine learning systems like neural networks are both abundant in everyday life. While classic computer science algorithms are suitable for precise executio…
Differentiable Top-k Classification Learning
Felix Petersen, Hilde Kuehne, Christian Borgelt +1
The top-k classification accuracy is one of the core metrics in machine learning. Here, k is conventionally a positive integer, such as 1 or 5, leading to top-1 or top-5 training o…
Domain Adaptation meets Individual Fairness. And they get along
Debarghya Mukherjee, Felix Petersen, Mikhail Yurochkin +1
Many instances of algorithmic bias are caused by distributional shifts. For example, machine learning (ML) models often perform worse on demographic groups that are underrepresente…
GenDR: A Generalized Differentiable Renderer
Felix Petersen, Bastian Goldluecke, Christian Borgelt +1
In this work, we present and study a generalized family of differentiable renderers. We discuss from scratch which components are necessary for differentiable rendering and formali…
Monotonic Differentiable Sorting Networks
Felix Petersen, Christian Borgelt, Hilde Kuehne +1
Differentiable sorting algorithms allow training with sorting and ranking supervision, where only the ordering or ranking of samples is known. Various methods have been proposed to…
Post-processing for Individual Fairness
Felix Petersen, Debarghya Mukherjee, Yuekai Sun +1
Post-processing in algorithmic fairness is a versatile approach for correcting bias in ML systems that are already used in production. The main appeal of post-processing is that it…
Learning with Algorithmic Supervision via Continuous Relaxations
Felix Petersen, Christian Borgelt, Hilde Kuehne +1
The integration of algorithmic components into neural architectures has gained increased attention recently, as it allows training neural networks with new forms of supervision suc…
Style Agnostic 3D Reconstruction via Adversarial Style Transfer
Felix Petersen, Bastian Goldluecke, Oliver Deussen +1
Reconstructing the 3D geometry of an object from an image is a major challenge in computer vision. Recently introduced differentiable renderers can be leveraged to learn the 3D geo…
Differentiable Sorting Networks for Scalable Sorting and Ranking Supervision
Felix Petersen, Christian Borgelt, Hilde Kuehne +1
Sorting and ranking supervision is a method for training neural networks end-to-end based on ordering constraints. That is, the ground truth order of sets of samples is known, whil…
AlgoNet: Smooth Algorithmic Neural Networks
Felix Petersen, Christian Borgelt, Oliver Deussen
Artificial neural networks revolutionized many areas of computer science in recent years since they provide solutions to a number of previously unsolved problems. On the other hand…
Pix2Vex: Image-to-Geometry Reconstruction using a Smooth Differentiable Renderer
Felix Petersen, Amit H. Bermano, Oliver Deussen +1
The long-coveted task of reconstructing 3D geometry from images is still a standing problem. In this paper, we build on the power of neural networks and introduce Pix2Vex, a networ…
Towards Formula Translation using Recursive Neural Networks
Felix Petersen, Moritz Schubotz, Bela Gipp
While it has become common to perform automated translations on natural language, performing translations between different representations of mathematical formulae has thus far no…