65 citations · 132 across the 23 of their papers we have counts for
26 papers
Spectral Signatures of Memorization Basins in Diffusion Trajectories
Achref Jaziri, Martin Mundt, Ahmed Imtiaz Humayun +1
Diffusion models are known to reproduce individual examples from their training data as a form of memorization with implications for generalization, privacy, and downstream use. Re…
Beyond Binary Out-of-Distribution Detection: Characterizing Distributional Shifts with Multi-Statistic Diffusion Trajectories
Achref Jaziri, Martin Rogmann, Martin Mundt +1
Detecting out-of-distribution (OOD) data is critical for machine learning, be it for safety reasons or to enable open-ended learning. However, beyond mere detection, choosing an ap…
Scaling Probabilistic Circuits via Data Partitioning
Jonas Seng, Florian Peter Busch, Pooja Prasad +3
Probabilistic circuits (PCs) enable us to learn joint distributions over a set of random variables and to perform various probabilistic queries in a tractable fashion. Though the t…
The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation
Martin Mundt, Anaelia Ovalle, Felix Friedrich +5
In a widely popular analogy by Turing Award Laureate Yann LeCun, machine intelligence has been compared to cake - where unsupervised learning forms the base, supervised learning ad…
Core Tokensets for Data-efficient Sequential Training of Transformers
Subarnaduti Paul, Manuel Brack, Patrick Schramowski +2
Deep networks are frequently tuned to novel tasks and continue learning from ongoing data streams. Such sequential training requires consolidation of new and past information, a ch…
Where is the Truth? The Risk of Getting Confounded in a Continual World
Florian Peter Busch, Roshni Kamath, Rupert Mitchell +3
A dataset is confounded if it is most easily solved via a spurious correlation, which fails to generalize to new data. In this work, we show that, in a continual learning setting w…
BOWL: A Deceptively Simple Open World Learner
Roshni . R. Kamath, Rupert Mitchell, Subarnaduti Paul +2
Traditional machine learning excels on static benchmarks, but the real world is dynamic and seldom as carefully curated as test sets. Practical applications may generally encounter…
Designing a Hybrid Neural System to Learn Real-world Crack Segmentation from Fractal-based Simulation
Achref Jaziri, Martin Mundt, Andres Fernandez Rodriguez +1
Identification of cracks is essential to assess the structural integrity of concrete infrastructure. However, robust crack segmentation remains a challenging task for computer visi…
Self-Expanding Neural Networks
Rupert Mitchell, Robin Menzenbach, Kristian Kersting +1
The results of training a neural network are heavily dependent on the architecture chosen; and even a modification of only its size, however small, typically involves restarting th…
Masked Autoencoders are Efficient Continual Federated Learners
Subarnaduti Paul, Lars-Joel Frey, Roshni Kamath +2
Machine learning is typically framed from a perspective of i.i.d., and more importantly, isolated data. In parts, federated learning lifts this assumption, as it sets out to solve…
Deep Classifier Mimicry without Data Access
Steven Braun, Martin Mundt, Kristian Kersting
Access to pre-trained models has recently emerged as a standard across numerous machine learning domains. Unfortunately, access to the original data the models were trained on may…
Queer In AI: A Case Study in Community-Led Participatory AI
Organizers Of QueerInAI, :, Anaelia Ovalle +48
We present Queer in AI as a case study for community-led participatory design in AI. We examine how participatory design and intersectional tenets started and shaped this community…
Probabilistic Circuits That Know What They Don't Know
Fabrizio Ventola, Steven Braun, Zhongjie Yu +2
Probabilistic circuits (PCs) are models that allow exact and tractable probabilistic inference. In contrast to neural networks, they are often assumed to be well-calibrated and rob…
FEATHERS: Federated Architecture and Hyperparameter Search
Jonas Seng, Pooja Prasad, Martin Mundt +2
Deep neural architectures have profound impact on achieved performance in many of today's AI tasks, yet, their design still heavily relies on human prior knowledge and experience.…
CLEVA-Compass: A Continual Learning EValuation Assessment Compass to Promote Research Transparency and Comparability
Martin Mundt, Steven Lang, Quentin Delfosse +1
What is the state of the art in continual machine learning? Although a natural question for predominant static benchmarks, the notion to train systems in a lifelong manner entails…
A Procedural World Generation Framework for Systematic Evaluation of Continual Learning
Timm Hess, Martin Mundt, Iuliia Pliushch +1
Several families of continual learning techniques have been proposed to alleviate catastrophic interference in deep neural network training on non-stationary data. However, a compr…
When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics
Iuliia Pliushch, Martin Mundt, Nicolas Lupp +1
Although a plethora of architectural variants for deep classification has been introduced over time, recent works have found empirical evidence towards similarities in their traini…
Neural Architecture Search of Deep Priors: Towards Continual Learning without Catastrophic Interference
Martin Mundt, Iuliia Pliushch, Visvanathan Ramesh
In this paper we analyze the classification performance of neural network structures without parametric inference. Making use of neural architecture search, we empirically demonstr…
Avalanche: an End-to-End Library for Continual Learning
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu +25
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing…
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Quentin Delfosse, Patrick Schramowski, Martin Mundt +2
Latest insights from biology show that intelligence not only emerges from the connections between neurons but that individual neurons shoulder more computational responsibility tha…
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning
Martin Mundt, Yongwon Hong, Iuliia Pliushch +1
Current deep learning methods are regarded as favorable if they empirically perform well on dedicated test sets. This mentality is seamlessly reflected in the resurfacing area of c…
Open Set Recognition Through Deep Neural Network Uncertainty: Does Out-of-Distribution Detection Require Generative Classifiers?
Martin Mundt, Iuliia Pliushch, Sagnik Majumder +1
We present an analysis of predictive uncertainty based out-of-distribution detection for different approaches to estimate various models' epistemic uncertainty and contrast it with…
Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognition
Martin Mundt, Iuliia Pliushch, Sagnik Majumder +2
Modern deep neural networks are well known to be brittle in the face of unknown data instances and recognition of the latter remains a challenge. Although it is inevitable for cont…
Meta-learning Convolutional Neural Architectures for Multi-target Concrete Defect Classification with the COncrete DEfect BRidge IMage Dataset
Martin Mundt, Sagnik Majumder, Sreenivas Murali +2
Recognition of defects in concrete infrastructure, especially in bridges, is a costly and time consuming crucial first step in the assessment of the structural integrity. Large var…