arXiv subjects

Katarzyna Wasielewska-Michniewska

Publications and source records attributed to Katarzyna Wasielewska-Michniewska.

6 recordsLinked to original sources

arXiv2026

Semantic Radiance Fields as Simulators for Spatial Reasoning in Real-World Scenes

Training and evaluating spatial reasoning in embodied agents requires diverse environments that are both geometrically faithful and semantically queryable. Synthetic simulators offer ground truth semantics but sacrifice realism; simulators based on reconstructions of real-world environments have realistic appearance but lack ground truth semantics by default. We propose using Semantic Radiance Fields (SRF) as simulators for spatial reasoning agents. SRFs are a representation that unifies these requirements by lifting 2D semantic segmentations from pretrained vision models into a 3D radiance field that jointly encodes geometry, appearance, and per-class semantic identity. The resulting fields are reconstructed from posed RGB captures of real scenes and support novel-view synthesis, semantic and free-space queries within a single grounded representation. This enables the efficient generation of diverse real-world environments to train and evaluate spatial reasoning models. As an example application, we outline an SRF-driven simulator for an orchard apple-reaching task, in which the radiance field supplies camera rendering, semantic ground truth, and occupancy queries to a physics engine.

cs.RO↗

arXiv2025

ReReLRP -- Remembering and Recognizing Tasks with LRP

Deep neural networks have revolutionized numerous research fields and applications. Despite their widespread success, a fundamental limitation known as catastrophic forgetting remains, where models fail to retain their ability to perform previously learned tasks after being trained on new ones. This limitation is particularly acute in certain continual learning scenarios, where models must integrate the knowledge from new domains with their existing capabilities. Traditional approaches to mitigate this problem typically rely on memory replay mechanisms, storing either original data samples, prototypes, or activation patterns. Although effective, these methods often introduce significant computational overhead, raise privacy concerns, and require the use of dedicated architectures. In this work we present ReReLRP (Remembering and Recognizing with LRP), a novel solution that leverages Layerwise Relevance Propagation (LRP) to preserve information across tasks. Our contribution provides increased privacy of existing replay-free methods while additionally offering built-in explainability, flexibility of model architecture and deployment, and a new mechanism to increase memory storage efficiency. We validate our approach on a wide variety of datasets, demonstrating results comparable with a well-known replay-based method in selected scenarios.

cs.LG↗

arXiv2022

Introducing Federated Learning into Internet of Things ecosystems -- preliminary considerations

Federated learning (FL) was proposed to facilitate the training of models in a distributed environment. It supports the protection of (local) data privacy and uses local resources for model training. Until now, the majority of research has been devoted to "core issues", such as adaptation of machine learning algorithms to FL, data privacy protection, or dealing with the effects of uneven data distribution between clients. This contribution is anchored in a practical use case, where FL is to be actually deployed within an Internet of Things ecosystem. Hence, somewhat different issues that need to be considered, beyond popular considerations found in the literature, are identified. Moreover, an architecture that enables the building of flexible, and adaptable, FL solutions is introduced.

cs.LG↗

arXiv2022

Efficient RDF Streaming for the Edge-Cloud Continuum

With the ongoing, gradual shift of large-scale distributed systems towards the edge-cloud continuum, the need arises for software solutions that are universal, scalable, practical, and grounded in well-established technologies. Simultaneously, semantic technologies, especially in the streaming context, are becoming increasingly important for enabling interoperability in edge-cloud systems. However, in recent years, the field of semantic data streaming has been stagnant, and there are no available solutions that would fit those requirements. To fill this gap, in this contribution, a novel end-to-end RDF streaming approach is proposed (named Jelly). The method is simple to implement, yet very elastic, and designed to fit a wide variety of use cases. Its practical performance is evaluated in a series of experiments, including end-to-end throughput and latency measurements. It is shown that Jelly achieves vastly superior performance to the currently available approaches. The presented method makes significant progress towards enabling high-performance semantic data processing in a wide variety of applications, including future edge-cloud systems. Moreover, this study opens up the possibility of applying and evaluating the method in real-life scenarios, which will be the focus of further research.

cs.DB↗

arXiv2022

Ontology Reuse: the Real Test of Ontological Design

Reusing ontologies in practice is still very challenging, especially when multiple ontologies are (jointly) involved. Moreover, despite recent advances, the realization of systematic ontology quality assurance remains a difficult problem. In this work, the quality of thirty biomedical ontologies, and the Computer Science Ontology are investigated, from the perspective of a practical use case. Special scrutiny is given to cross-ontology references, which are vital for combining ontologies. Diverse methods to detect potential issues are proposed, including natural language processing and network analysis. Moreover, several suggestions for improving ontologies and their quality assurance processes are presented. It is argued that while the advancing automatic tools for ontology quality assurance are crucial for ontology improvement, they will not solve the problem entirely. It is ontology reuse that is the ultimate method for continuously verifying and improving ontology quality, as well as for guiding its future development. Specifically, multiple issues can be found and fixed primarily through practical and diverse ontology reuse scenarios.

cs.SE↗

arXiv2022

Topical Classification of Food Safety Publications with a Knowledge Base

The vast body of scientific publications presents an increasing challenge of finding those that are relevant to a given research question, and making informed decisions on their basis. This becomes extremely difficult without the use of automated tools. Here, one possible area for improvement is automatic classification of publication abstracts according to their topic. This work introduces a novel, knowledge base-oriented publication classifier. The proposed method focuses on achieving scalability and easy adaptability to other domains. Classification speed and accuracy are shown to be satisfactory, in the very demanding field of food safety. Further development and evaluation of the method is needed, as the proposed approach shows much potential.

cs.CL↗