Maxim Bonnaerens
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Maxim Bonnaerens has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Joni Dambre
Ghent University
2 shared publications - Matthias Freiberger
Copenhagen University, Denmark
2 shared publications Joni Dambre
1 shared publication- Marian Verhelst
KU Leuven
1 shared publication
Latest Publications
- Open Access
Learned Thresholds Token Merging and Pruning for Vision Transformers
Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years. However, their high computational costs remain a significant barrier to their practical deployment. In particular, the complexity of transformer models is quadratic with respect to the number of input tokens. Therefore techniques that reduce the number of input tokens that need to be processed have been proposed. This paper introduces Learned Thresholds token Merging and Pruning (LTMP), a novel approach that leverages the strengths of both token merging and token pruning. LTMP uses learned threshold masking modules that dynamically determine which tokens to merge and which to prune. We demonstrate our approach with extensive experiments on vision transformers on the ImageNet classification task. Our results demonstrate that LTMP achieves state-of-the-art accuracy across reduction rates while requiring only a single fine-tuning epoch, which is an order of magnitude faster than previous methods. Code is available at https://github.com/Mxbonn/ltmp .
Open AccessLearned Thresholds Token Merging and Pruning for Vision Transformers
Vision transformers have demonstrated remarkable success in a wide range of computer vision tasks over the last years. However, their high computational costs remain a significant barrier to their practical deployment. In particular, the complexity of transformer models is quadratic with respect to the number of input tokens. Therefore techniques that reduce the number of input tokens that need to be processed have been proposed. This paper introduces Learned Thresholds token Merging and Pruning (LTMP), a novel approach that leverages the strengths of both token merging and token pruning. LTMP uses learned threshold masking modules that dynamically determine which tokens to merge and which to prune. We demonstrate our approach with extensive experiments on vision transformers on the ImageNet classification task. Our results demonstrate that LTMP achieves state-of-the-art accuracy across reduction rates while requiring only a single fine-tuning epoch, which is an order of magnitude faster than previous methods. Code is available at https://github.com/Mxbonn/ltmp .
- Open Access
- 9 December 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (24) , 12615
Hardware-Aware Mobile Building Block Evaluation for Computer Vision
In this paper, we propose a methodology to accurately evaluate and compare the performance of efficient neural network building blocks for computer vision in a hardware-aware manner. Our comparison uses pareto fronts based on randomly sampled networks from a design space to capture the underlying accuracy/complexity trade-offs. We show that our approach enables matching of information obtained by previous comparison paradigms, but provides more insights into the relationship between hardware cost and accuracy. We use our methodology to analyze different building blocks and evaluate their performance on a range of embedded hardware platforms. This highlights the importance of benchmarking building blocks as a preselection step in the design process of a neural network. We show that choosing the right building block can speed up inference by up to a factor of two on specific hardware ML accelerators.
- 9 December 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (24) , 12615
Open AccessHardware-Aware Mobile Building Block Evaluation for Computer Vision
In this paper, we propose a methodology to accurately evaluate and compare the performance of efficient neural network building blocks for computer vision in a hardware-aware manner. Our comparison uses pareto fronts based on randomly sampled networks from a design space to capture the underlying accuracy/complexity trade-offs. We show that our approach enables matching of information obtained by previous comparison paradigms, but provides more insights into the relationship between hardware cost and accuracy. We use our methodology to analyze different building blocks and evaluate their performance on a range of embedded hardware platforms. This highlights the importance of benchmarking building blocks as a preselection step in the design process of a neural network. We show that choosing the right building block can speed up inference by up to a factor of two on specific hardware ML accelerators.
- Open Access
- 20 May 2022
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 221
Anchor pruning for object detection
- 20 May 2022
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 221
Open AccessAnchor pruning for object detection