Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Pahde, Frederik"'
Autor:
Mekala, Rohan Reddy, Pahde, Frederik, Baur, Simon, Chandrashekar, Sneha, Diep, Madeline, Wenzel, Markus, Wisotzky, Eric L., Yolcu, Galip Ümit, Lapuschkin, Sebastian, Ma, Jackie, Eisert, Peter, Lindvall, Mikael, Porter, Adam, Samek, Wojciech
In the realm of dermatological diagnoses, where the analysis of dermatoscopic and microscopic skin lesion images is pivotal for the accurate and early detection of various medical conditions, the costs associated with creating diverse and high-qualit
Externí odkaz:
http://arxiv.org/abs/2410.05114
Autor:
Tinauer, Christian, Damulina, Anna, Sackl, Maximilian, Soellradl, Martin, Achtibat, Reduan, Dreyer, Maximilian, Pahde, Frederik, Lapuschkin, Sebastian, Schmidt, Reinhold, Ropele, Stefan, Samek, Wojciech, Langkammer, Christian
Motivation. While recent studies show high accuracy in the classification of Alzheimer's disease using deep neural networks, the underlying learned concepts have not been investigated. Goals. To systematically identify changes in brain regions throug
Externí odkaz:
http://arxiv.org/abs/2404.10433
Autor:
Bareeva, Dilyara, Dreyer, Maximilian, Pahde, Frederik, Samek, Wojciech, Lapuschkin, Sebastian
Deep Neural Networks are prone to learning and relying on spurious correlations in the training data, which, for high-risk applications, can have fatal consequences. Various approaches to suppress model reliance on harmful features have been proposed
Externí odkaz:
http://arxiv.org/abs/2404.09601
Autor:
Dreyer, Maximilian, Pahde, Frederik, Anders, Christopher J., Samek, Wojciech, Lapuschkin, Sebastian
Deep Neural Networks are prone to learning spurious correlations embedded in the training data, leading to potentially biased predictions. This poses risks when deploying these models for high-stake decision-making, such as in medical applications. C
Externí odkaz:
http://arxiv.org/abs/2308.09437
State-of-the-art machine learning models often learn spurious correlations embedded in the training data. This poses risks when deploying these models for high-stake decision-making, such as in medical applications like skin cancer detection. To tack
Externí odkaz:
http://arxiv.org/abs/2303.12641
Autor:
Pahde, Frederik, Yolcu, Galip Ümit, Binder, Alexander, Samek, Wojciech, Lapuschkin, Sebastian
Explainable AI (XAI) is slowly becoming a key component for many AI applications. Rule-based and modified backpropagation XAI approaches however often face challenges when being applied to modern model architectures including innovative layer buildin
Externí odkaz:
http://arxiv.org/abs/2211.17174
Autor:
Pahde, Frederik, Dreyer, Maximilian, Weber, Leander, Weckbecker, Moritz, Anders, Christopher J., Wiegand, Thomas, Samek, Wojciech, Lapuschkin, Sebastian
With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space. Commonly, CAVs are computed by leveraging
Externí odkaz:
http://arxiv.org/abs/2202.03482
Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios. However, if data in additional modalities exist (e.g. text) this can compensate for the
Externí odkaz:
http://arxiv.org/abs/2011.08899
Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-art approaches are largely unsuitable in scarce data regimes. To addres
Externí odkaz:
http://arxiv.org/abs/1901.01868
State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes. To a certain extent this lack of data can be compensated by multimod
Externí odkaz:
http://arxiv.org/abs/1811.09192