321 citations · 420 across the 20 of their papers we have counts for
20 papers
Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoning
Sparsh Tiwari, Gesina Schwalbe, Bettina Finzel
Two-stage neuro-symbolic architectures provide an elegant paradigm for visual problem solving by cleanly separating connectionist perception of predefined symbols from possibly lat…
Weakly Supervised Concept Learning for Object-centric Visual Reasoning
Sparsh Tiwari, Bettina Finzel, Gesina Schwalbe
Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial intelligence. Two-stage approa…
Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein +8
Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this…
Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties
Raik Dankworth, Gesina Schwalbe
Deep neural networks (NNs) for computer vision are vulnerable to adversarial attacks, i.e., miniscule malicious changes to inputs may induce unintuitive outputs. One key approach t…
On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNs
Gesina Schwalbe, Georgii Mikriukov, Edgar Heinert +5
The thriving research field of concept-based explainable artificial intelligence (C-XAI) investigates how human-interpretable semantic concepts embed in the latent spaces of deep n…
Benchmarking Vision Foundation Models for Input Monitoring in Autonomous Driving
Mert Keser, Halil Ibrahim Orhan, Niki Amini-Naieni +3
Deep neural networks (DNNs) remain challenged by distribution shifts in complex open-world domains like automated driving (AD): Robustness against yet unknown novel objects (semant…
Unveiling Ontological Commitment in Multi-Modal Foundation Models
Mert Keser, Gesina Schwalbe, Niki Amini-Naieni +2
Ontological commitment, i.e., used concepts, relations, and assumptions, are a corner stone of qualitative reasoning (QR) models. The state-of-the-art for processing raw inputs, th…
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
Jae Hee Lee, Georgii Mikriukov, Gesina Schwalbe +2
Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising field of research, since explanations that refer to concepts (i.e., semantically meaningful…
Investigating Calibration and Corruption Robustness of Post-hoc Pruned Perception CNNs: An Image Classification Benchmark Study
Pallavi Mitra, Gesina Schwalbe, Nadja Klein
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks. However, high computational and storage demands hinder their deployme…
The Anatomy of Adversarial Attacks: Concept-based XAI Dissection
Georgii Mikriukov, Gesina Schwalbe, Franz Motzkus +1
Adversarial attacks (AAs) pose a significant threat to the reliability and robustness of deep neural networks. While the impact of these attacks on model predictions has been exten…
Local Concept Embeddings for Analysis of Concept Distributions in Vision DNN Feature Spaces
Georgii Mikriukov, Gesina Schwalbe, Korinna Bade
Insights into the learned latent representations are imperative for verifying deep neural networks (DNNs) in critical computer vision (CV) tasks. Therefore, state-of-the-art superv…
Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes
Youssef Shoeb, Robin Chan, Gesina Schwalbe +3
In the life cycle of highly automated systems operating in an open and dynamic environment, the ability to adjust to emerging challenges is crucial. For systems integrating data-dr…
Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert +1
Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks…
Evaluating the Stability of Semantic Concept Representations in CNNs for Robust Explainability
Georgii Mikriukov, Gesina Schwalbe, Christian Hellert +1
Analysis of how semantic concepts are represented within Convolutional Neural Networks (CNNs) is a widely used approach in Explainable Artificial Intelligence (XAI) for interpretin…
Concept Embedding Analysis: A Review
Gesina Schwalbe
Deep neural networks (DNNs) have found their way into many applications with potential impact on the safety, security, and fairness of human-machine-systems. Such require basic und…
Enabling Verification of Deep Neural Networks in Perception Tasks Using Fuzzy Logic and Concept Embeddings
Gesina Schwalbe, Christian Wirth, Ute Schmid
One major drawback of deep convolutional neural networks (CNNs) for use in safety critical applications is their black-box nature. This makes it hard to verify or monitor complex,…
Expressive Explanations of DNNs by Combining Concept Analysis with ILP
Johannes Rabold, Gesina Schwalbe, Ute Schmid
Explainable AI has emerged to be a key component for black-box machine learning approaches in domains with a high demand for reliability or transparency. Examples are medical assis…
Verification of Size Invariance in DNN Activations using Concept Embeddings
Gesina Schwalbe
The benefits of deep neural networks (DNNs) have become of interest for safety critical applications like medical ones or automated driving. Here, however, quantitative insights in…
A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
Gesina Schwalbe, Bettina Finzel
In the meantime, a wide variety of terminologies, motivations, approaches, and evaluation criteria have been developed within the research field of explainable artificial intellige…
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
Sebastian Houben, Stephanie Abrecht, Maram Akila +38
The use of deep neural networks (DNNs) in safety-critical applications like mobile health and autonomous driving is challenging due to numerous model-inherent shortcomings. These s…