She will work in the project "AI-DPA: Analyse und Interpretation von unstrukturierten Daten und Prozessen in zwei- und dreidimensionalen Anwendungsszenarien mit Machine Learning"
News-Archiv
Although I already started in Koblenz in 2022, I will now give my inaugural lecture with the title "Künstliche Intelligenz hat viele Dimensionen: Die Magie hochdimensionaler Vektorrepräsentationen für Roboter und andere autonome Systeme" (the lecture will be in German).
Anyone interested is warmly invited!
February 1, 18:00-20:00, Room M001, University Campus
A joint team from our group and researchers from Sweden and Australia has won the "My Seizure Gauge'' Challenge on forecasting epileptic seizures from non-cerebral signals. A short summary of the competition and our winning approach is provided in a paper that has been accepted for publication in Nature Machine Intelligence in the Challenge Accepted track. Congratulations to Kenny Schlegel who has led this team! The paper is a joint work of our team and the challenge organizers.
Kenny Schlegel, Denis Kleyko, Benjamin H. Brinkmann, Ewan S. Nurse, Ross W. Gayler, Peer Neubert (2024). Lessons from the “My Seizure Gauge” Challenge on Forecasting Epileptic Seizures from Non-Cerebral Signals. Nature Machine Intelligence Challenge Accepted (to appear)
The paper "Local positional graphs and attentive local features for a data and runtime-efficient hierarchical place recognition pipeline" by Fangming Yuan, Stefan Schubert, Peter Protze,l and Peer Neubert has been accepted for publication in IEEE RA-L journal.
Abstract: Large-scale applications of Visual Place Recognition (VPR) require computationally efficient approaches. Further, a well-balanced combination of data-based and training-free approaches can decrease the required amount of training data and effort and can reduce the influence of distribution shifts between the training and application phases. This paper proposes a runtime and data-efficient hierarchical VPR pipeline that extends existing approaches and presents novel ideas. There are three main contributions: First, we propose Local Positional Graphs (LPG), a training-free and runtime-efficient approach to encode spatial context information of local image features. LPG can be combined with existing local feature detectors and descriptors and considerably improves the image-matching quality compared to existing techniques in our experiments. Second, we present Attentive Local SPED (ATLAS), an extension of our previous local features approach with an attention module that improves the feature quality while maintaining high data efficiency. The influence of the proposed modifications is evaluated in an extensive ablation study. Third, we present a hierarchical pipeline that exploits hyperdimensional computing to use the same local features as holistic HDC-descriptors for fast candidate selection and for candidate reranking. We combine all contributions in a runtime and data-efficient VPR pipeline that shows benefits over the state-of-the-art method Patch-NetVLAD on a large collection of standard place recognition datasets with 15x better performance in VPR accuracy, 54x faster feature comparison speed, and 27x less descriptor storage occupancy, making our method promising for real-world high-performance large-scale VPR in changing environments. Code will be made available with publication of this paper.
Stefan Schubert - an external PhD student - successfully defended his PhD thesis at Chemnitz University of Technology with highest honours. Congratulations!
The paper "FETCH: A Memory-Efficient Replay Approach for Continual Learning in Image Classification" was accepted at IDEAL conference.
Abstract: 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, promising results were achieved using replay and compressed replay techniques. In the field of regular replay, GDumb [23] achieved outstanding results but requires a large amount of memory. This problem can be addressed by compressed replay techniques. The goal of this work is to evaluate compressed replay in the pipeline of GDumb. We propose FETCH, a two-stage compression approach. First, the samples from the continual datastream are encoded by the early layers of a pre-trained neural network. Second, the samples are compressed before being stored in the episodic memory. Following GDumb, the remaining classification head is trained from scratch using only the decompressed samples from the reply memory. We evaluate FETCH in different scenarios and show that this approach can increase accuracy on CIFAR10 and CIFAR100. In our experiments, simple compression methods (e.g., quantization of tensors) outperform deep autoencoders. In the future, FETCH could serve as a baseline for benchmarking compressed replay learning in constrained memory scenarios.
The KI-Forschungskolleg "AI-DPA: Analyse und Interpretation von unstrukturierten Daten und Prozessen in zwei- und dreidimensionalen Anwendungsszenarien mit Machine Learning" in cooperation with University of Applied Science Mainz started!
The paper "HealthWalk: Promoting Health and Mobility through Sensor-Based Rollator Walker Assistance" has been accepted at the ICCV workshop on Assistive Computer Vision and Robotics.
Abstract: Rollator walkers allow people with physical limitations to increase their mobility and give them the confidence and independence to participate in society for longer. However, rollator walker users often have poor posture, leading to further health problems and, in the worst case, falls.
The paper "Point-Cloud-Based Change Detection for Steep Slope Vineyard Agriculture" was accepted at the IEEE Sensors conference.
Abstract: In recent years, research and development has been focused on the digitalization and automation of farmland. One problem is the monitoring of the growth of the plants and in general the condition of agricultural areas like vineyards over time. In this paper we present an approach that utilizes change detection techniques from the field of remote sensing in order to support the cultivation of steep slopes in the Moselle wine-growing region. Data was collected with LIDAR sensor systems in three ways with a UAV from the air, as well as from the ground by a handheld device and by means of a caterpillar. We were able to show that by analyzing three-dimensional sensor data, conclusions could be made about the growth of vines, weeds and general changes in a vineyard.
The paper Visual Place Recognition: A Tutorial was accepted for publication in the IEEE Robotics and Automation Magazine (RAM).
Abstract: Localization is an essential capability for mobile robots, enabling them to build a comprehensive representation of their environment and interact with the environment effectively toward a goal. A rapidly growing field of research in this area is visual place recognition (VPR), which is the ability to recognize previously seen places in the world based solely on images.
The students' projects around robot Ada achieved 3rd place at the CV-day. Congratulations!
Kevin Weirauch joined our group!
We welcome the robot Ada as a new team member!
Mark O. Mints joined our group!