Tin Barisin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tin Barisin has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Claudia Redenbach
RPTU University Kaiserslautern-Landau
2 shared publications - Katja Schladitz
Fraunhofer-Institut für Techno-und Wirtschaftsmathematik (ITWM) Fraunhofer-Platz 1 67663 Kaiserslautern Germany
2 shared publications - Christian Jung
Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau (RPTU) Gottlieb-Daimler-Straße 47 67663 Kaiserslautern Germany
1 shared publication - Illia Horenko
Department of Mathematics, Artificial Intelligence in Mathematics, TU Kaiserslautern
1 shared publication - Juraj Fulir
Fraunhofer ITWM Germany
1 shared publication Katja Schladitz
Image Processing Department, Kaiserslautern, Germany
1 shared publication
Latest Publications
- 8 August 2025
- Published by MIT Press in Neural Computation
- Vol. 37 (9) , 1648-1676
Toward Generalized Entropic Sparsification for Convolutional Neural Networks
Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem: if the network has N neurons, then there are 2N possibilities to connect them—and therefore 2N possible architectures and 2N Boolean hyperparameters to encode them. Selecting the best possible hyperparameter out of them becomes an Np-hard problem since 2N grows in N faster then any polynomial Np. Here, we introduce a layer-by-layer data-driven pruning method based on the mathematical idea aiming at a computationally scalable entropic relaxation of the pruning problem. The sparse subnetwork is found from the pretrained (full) CNN using the network entropy minimization as a sparsity constraint. This allows deploying a numerically scalable algorithm with a sublinear scaling cost. The method is validated on several benchmarks (architectures): on MNIST (LeNet), resulting in sparsity of 55% to 84% and loss in accuracy of just 0.1% to 0.5%, and on CIFAR-10 (VGG-16, ResNet18), resulting in sparsity of 73% to 89% and loss in accuracy of 0.1% to 0.5%.
- 8 August 2025
- Published by MIT Press in Neural Computation
- Vol. 37 (9) , 1648-1676
Toward Generalized Entropic Sparsification for Convolutional Neural Networks
Convolutional neural networks (CNNs) are reported to be overparametrized. The search for optimal (minimal) and sufficient architecture is an NP-hard problem: if the network has N neurons, then there are 2N possibilities to connect them—and therefore 2N possible architectures and 2N Boolean hyperparameters to encode them. Selecting the best possible hyperparameter out of them becomes an Np-hard problem since 2N grows in N faster then any polynomial Np. Here, we introduce a layer-by-layer data-driven pruning method based on the mathematical idea aiming at a computationally scalable entropic relaxation of the pruning problem. The sparse subnetwork is found from the pretrained (full) CNN using the network entropy minimization as a sparsity constraint. This allows deploying a numerically scalable algorithm with a sublinear scaling cost. The method is validated on several benchmarks (architectures): on MNIST (LeNet), resulting in sparsity of 55% to 84% and loss in accuracy of just 0.1% to 0.5%, and on CIFAR-10 (VGG-16, ResNet18), resulting in sparsity of 73% to 89% and loss in accuracy of 0.1% to 0.5%.
- 24 September 2024
- Published by Springer Nature
- p. 243-256
Simulation of Microstructures and Machine Learning
- 24 September 2024
- Published by Springer Nature
- p. 243-256
Simulation of Microstructures and Machine Learning
- Open Access
- 29 February 2024
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 66 (3) , 246-270
Riesz Networks: Scale-Invariant Neural Networks in a Single Forward Pass
Scale invariance of an algorithm refers to its ability to treat objects equally independently of their size. For neural networks, scale invariance is typically achieved by data augmentation. However, when presented with a scale far outside the range covered by the training set, neural networks may fail to generalize. Here, we introduce the Riesz network, a novel scale- invariant neural network. Instead of standard 2d or 3d convolutions for combining spatial information, the Riesz network is based on the Riesz transform which is a scale-equivariant operation. As a consequence, this network naturally generalizes to unseen or even arbitrary scales in a single forward pass. As an application example, we consider detecting and segmenting cracks in tomographic images of concrete. In this context, ‘scale’ refers to the crack thickness which may vary strongly even within the same sample. To prove its scale invariance, the Riesz network is trained on one fixed crack width. We then validate its performance in segmenting simulated and real tomographic images featuring a wide range of crack widths. An additional experiment is carried out on the MNIST Large Scale data set.
- 29 February 2024
- Published by Springer Nature in Journal of Mathematical Imaging and Vision
- Vol. 66 (3) , 246-270
Open AccessRiesz Networks: Scale-Invariant Neural Networks in a Single Forward Pass
Scale invariance of an algorithm refers to its ability to treat objects equally independently of their size. For neural networks, scale invariance is typically achieved by data augmentation. However, when presented with a scale far outside the range covered by the training set, neural networks may fail to generalize. Here, we introduce the Riesz network, a novel scale- invariant neural network. Instead of standard 2d or 3d convolutions for combining spatial information, the Riesz network is based on the Riesz transform which is a scale-equivariant operation. As a consequence, this network naturally generalizes to unseen or even arbitrary scales in a single forward pass. As an application example, we consider detecting and segmenting cracks in tomographic images of concrete. In this context, ‘scale’ refers to the crack thickness which may vary strongly even within the same sample. To prove its scale invariance, the Riesz network is trained on one fixed crack width. We then validate its performance in segmenting simulated and real tomographic images featuring a wide range of crack widths. An additional experiment is carried out on the MNIST Large Scale data set.
- Open Access
- 11 October 2023
- Published by Springer Nature in Materials and Structures
- Vol. 56 (9) , 1-18
Analysis of the bond behavior of a GFRP rebar in concrete by in-situ 3D imaging test
Computed tomography combined with mechanical tests offers completely new insight into the behavior of concrete samples under stress. Particularly the development of new fiber reinforcement materials for concrete elements requires appropriate material models and thus for investigating the interior of the concrete structure. In 3D image data obtained by computed tomography, local structural changes within the sample due to mechanical loading can be observed without further altering the sample. We applied this state-of-the-art approach to a concrete core with an embedded glass fiber reinforced polymer rebar under increasing forces applied to pull out the rebar. In this paper, authors describe a novel in-situ setup for non-destructively 3D imaging during the pull-out test. Conducting the pull-out test leads to the formation of local pore volume changes along the rebar. These pore volume changes are not only visualized but quantified analytically based on the images. Interpreting these volume changes, we derive a novel method for calculating strain and normal stresses in the rebar. Our new method captures the detailed distribution of the bond stresses between rebar and concrete and consequently describes the bond behavior more accurate. It turns out that the observed bond behavior cannot be explained completely by commonly assumed material laws. This emphasizes the need for further, more extensive research combining 3D imaging, mechanical testing, and quantitative image analysis.
- 11 October 2023
- Published by Springer Nature in Materials and Structures
- Vol. 56 (9) , 1-18
Open AccessAnalysis of the bond behavior of a GFRP rebar in concrete by in-situ 3D imaging test
Computed tomography combined with mechanical tests offers completely new insight into the behavior of concrete samples under stress. Particularly the development of new fiber reinforcement materials for concrete elements requires appropriate material models and thus for investigating the interior of the concrete structure. In 3D image data obtained by computed tomography, local structural changes within the sample due to mechanical loading can be observed without further altering the sample. We applied this state-of-the-art approach to a concrete core with an embedded glass fiber reinforced polymer rebar under increasing forces applied to pull out the rebar. In this paper, authors describe a novel in-situ setup for non-destructively 3D imaging during the pull-out test. Conducting the pull-out test leads to the formation of local pore volume changes along the rebar. These pore volume changes are not only visualized but quantified analytically based on the images. Interpreting these volume changes, we derive a novel method for calculating strain and normal stresses in the rebar. Our new method captures the detailed distribution of the bond stresses between rebar and concrete and consequently describes the bond behavior more accurate. It turns out that the observed bond behavior cannot be explained completely by commonly assumed material laws. This emphasizes the need for further, more extensive research combining 3D imaging, mechanical testing, and quantitative image analysis.