Intelligent Autonomous Systems (INTAS)

The paper "Cross-domain transfer of hyperspectral foundation models" by Nick Theisen and Peer Neubert has been accepted at the ICPR 2026 conference.

Abstract: Hyperspectral imaging (HSI) semantic segmentation typically relies on in-domain training, but limited data availability often restricts model performance in real-world applications. Current approaches to leverage foundation models in proximal sensing use cross-modality techniques, bridging RGB and HSI to exploit vision foundation models. However, these methods either discard spectral information or introduce architectural complexity. We propose cross-domain transfer as an alternative, reusing HSI foundation models – originally trained in remote sensing – for proximal sensing applications. By eliminating the need to bridge modality gaps, our approach preserves spectral information while maintaining a simple architecture. Using the HS3-Bench benchmark, we systematically evaluate and compare conventional in-domain, in-modality training, cross-modality transfer and cross-domain transfer strategies. Our results demonstrate that cross-domain transfer achieves large performance improvements over in-domain, in-modality training, reduces the performance gap to cross-modality approaches and maintains strong performance in limited data settings. Thus, this work advances more effective HSI semantic segmentation in diverse applications.

Preprint: https://arxiv.org/pdf/2604.26478

We are part of the successfull proposal in the DFG Major Research Instrumentation program by Maik Kschischo for extention of the compute server infrastructure at University of Koblenz.

Richard is going to work in the ViPRICE-Space project.

The research project "ViPRICE-Space: Visual Place recognition in changing environments" on visual localization in challenging space-analog environments achieved funding by the German Federal Ministry of Research, Technology and Space. The goal of this project is to bridge the research gap in Visual Place Recognition by transferring state-of-the-art VPR performance from terrestrial to extraterrestrial environments. These environments present unique challenges, including highly repetitive structures, sparse visual and semantic features, severe perceptual aliasing, and extreme illumination conditions. The project aims to develop robust place recognition methods capable of reliable operation under these demanding conditions while potentially exploiting different visual sensor modalities.

RA-L is one of the leading venues for publishing research in robotics and automation. It is known for its rapid review and publication process, making it popular for researchers who want timely dissemination of new results. Peer Neubert joined the editorial board in the area Visual Perception and Learning.

Congratulation to Dr. Fangming Yuan for successfully finishing his PhD thesis on "Runtime and Data-efficient Large-scale Hierarchical Visual Place Recognition for Changing Environments". He is now working at Neura Robotics.

Peer Neubert is guest editor for a Nature npj unconventional computing collection on "Hyperdimensional Computing and Vector Symbolic Architectures". This collection invites contributions reporting both theoretical and practical advances in HDC/VSA, particularly those aligned with the broad theme of unconventional computing. Submission is open until September 16, 2026 https://www.nature.com/collections/ijiiiahgdi

The paper "Structured temporal representation in time series classification with ROCKETs and Hyperdimensional Computing" by Kenny Schlegel, Dmitri A. Rachkovskij, Denis Kleyko,Ross W. Gayler, Peter Protzel, and Peer Neubert has been accepted for publication in the Data Mining and Knowledge Discovery journal.

Abstract: Time series classification poses significant challenges due to the inherent temporal order of the data points and the existence of sequential dependencies between them. The ROCKET family, featuring methods like MiniROCKET, MultiROCKET, and HYDRA, is currently a leading approach in this domain, leveraging convolution kernels to aggregate temporal features into encodings for linear classifiers. However, these models encode temporal features over short temporal windows and then aggregate them as an unordered set of encodings over the longer temporal window of the entire data sequence. This prevents these models from capturing any longer sequence structure. To address this design drawback, we propose integrating hyperdimensional computing into ROCKET methods to explicitly incorporate temporal order of the short-term features within the entire time series. This approach enhances the discriminative power of encodings generated by MiniROCKET, MultiROCKET, and HYDRA where longer-term structure exists in the data, leading to increased classification performance with minimal computational overhead. More specifically, we introduce a method to represent time series as high-dimensional vectors through multiplicative binding of ROCKET encodings with encodings representing temporal order, applying this approach across various ROCKET methods. Additionally, we explore different high-dimensional vector representations of temporal order, yielding diverse similarity kernels that enhance classification accuracy. Through experiments on synthetic datasets, we highlight the limitations of ROCKET methods in handling temporal dependencies and show how the methods based on hyperdimensional computing overcome these limitations. Furthermore, our extensive experimental evaluation with real-world datasets included in the recent UCR archive [1] and additional datasets from [2], validates the advantages of our approach, consistently achieving classification improvements across all ROCKET methods that integrate hyperdimensional computing. Notably, our best model achieves a relative error rate reduction of over 50% compared to the best ROCKET model on several UCR datasets.