111 citations · 273 across the 13 of their papers we have counts for
14 papers
FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classification
Markus Weißflog, Peter Protzel, Peer Neubert
Class-incremental continual learning is an important area of research, as static deep learning methods fail to adapt to changing tasks and data distributions. In previous works, pr…
Towards Revisiting Visual Place Recognition for Joining Submaps in Multimap SLAM
Markus Weißflog, Stefan Schubert, Peter Protzel +1
Visual SLAM is a key technology for many autonomous systems. However, tracking loss can lead to the creation of disjoint submaps in multimap SLAM systems like ORB-SLAM3. Because of…
Local positional graphs and attentive local features for a data and runtime-efficient hierarchical place recognition pipeline
Fangming Yuan, Stefan Schubert, Peter Protzel +1
Large-scale applications of Visual Place Recognition (VPR) require computationally efficient approaches. Further, a well-balanced combination of data-based and training-free approa…
A Credible and Robust approach to Ego-Motion Estimation using an Automotive Radar
Karim Haggag, Sven Lange, Tim Pfeifer +1
Consistent motion estimation is fundamental for all mobile autonomous systems. While this sounds like an easy task, often, it is not the case because of changing environmental cond…
HDC-MiniROCKET: Explicit Time Encoding in Time Series Classification with Hyperdimensional Computing
Kenny Schlegel, Peer Neubert, Peter Protzel
Classification of time series data is an important task for many application domains. One of the best existing methods for this task, in terms of accuracy and computation time, is…
Advancing Mixture Models for Least Squares Optimization
Tim Pfeifer, Sven Lange, Peter Protzel
Gaussian mixtures are a powerful and widely used tool to model non-Gaussian estimation problems. They are able to describe measurement errors that follow arbitrary distributions an…