Efficient AI

We improve the training of vision transformers by segmenting and recombining objects and backgrounds from datasets. This makes the transformers more accurate, as well as more robust.

Presentation at WACV 2025 on a large-scale benchmark of 45+ transformer models for image classification, evaluating accuracy, speed, and memory efficiency.

A comprehensive benchmark and analysis of more than 45 transformer models for image classification to evaluate their efficiency, considering various performance metrics. We find the optimal architectures to use and uncover that model-scaling is more efficient than image scaling.

This paper introduces TaylorShift, a novel reformulation of the attention mechanism using Taylor softmax that enables computing full token-to-token interactions in linear time. We analytically and empirically determine the crossover points where employing TaylorShift becomes more efficient than traditional attention. TaylorShift outperforms the traditional transformer architecture in 4 out of 5 tasks.

Oral presentation at ICPR 2024 introducing TaylorShift, a novel reformulation of the attention mechanism using Taylor-Softmax that enables full token-to-token interactions in linear time.

We speed up diffusion classifiers by utilizing a label hierarchy and pruning unrelated paths.

SustainML is dedicated to creating a sustainable ML framework for Green AI. By prioritizing energy efficiency, SustainML aims to pave the way for environmentally conscious AI solutions that are both efficient and effective.

Energy- and data-saving methods for environmental perception in embedded AI systems using the case study of smart factory and smart farming applications; funded by the Carl Zeiss Foundation.