TY - JOUR A1 - Väth, Philipp A1 - Frühwald, Alexander M. A1 - Paaßen, Benjamin A1 - Gregorová, Magda T1 - Diffusion-based Visual Counterfactual Explanations - Towards Systematic Quantitative Evaluation JF - CoRR N2 - Latest methods for visual counterfactual explanations (VCE) harness the power of deep generative models to synthesize new examples of high-dimensional images of impressive quality. However, it is currently difficult to compare the performance of these VCE methods as the evaluation procedures largely vary and often boil down to visual inspection of individual examples and small scale user studies. In this work, we propose a framework for systematic, quantitative evaluation of the VCE methods and a minimal set of metrics to be used. We use this framework to explore the effects of certain crucial design choices in the latest diffusion-based generative models for VCEs of natural image classification (ImageNet). We conduct a battery of ablation-like experiments, generating thousands of VCEs for a suite of classifiers of various complexity, accuracy and robustness. Our findings suggest multiple directions for future advancements and improvements of VCE methods. By sharing our methodology and our approach to tackle the computational challenges of such a study on a limited hardware setup (including the complete code base), we offer a valuable guidance for researchers in the field fostering consistency and transparency in the assessment of counterfactual explanations. Y1 - 2023 U6 - https://doi.org/10.48550/arXiv.2308.06100 VL - abs/2308.06100 ER - TY - JOUR A1 - Väth, Philipp A1 - Frühwald, Alexander M. A1 - Paassen, Benjamin A1 - Gregorová, Magda T1 - GradCheck: Analyzing classifier guidance gradients for conditional diffusion sampling JF - CoRR Y1 - 2024 U6 - https://doi.org/10.48550/ARXIV.2406.17399 VL - abs/2406.17399 ER - TY - JOUR A1 - Väth, Philipp A1 - Frühwald, Alexander M. A1 - Paassen, Benjamin A1 - Gregorová, Magda T1 - Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability JF - CoRR Y1 - 2024 U6 - https://doi.org/10.48550/ARXIV.2410.20890 VL - abs/2410.20890 ER - TY - CHAP A1 - Ewecker, Lukas A1 - Winkler, Timo A1 - Väth, Philipp A1 - Schwager, Robin A1 - Brühl, Tim A1 - Schleif, Frank-Michael T1 - How Important is the Temporal Context to Anticipate Oncoming Vehicles at Night? T2 - IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023, Honolulu, Oahu, HI, USA, October 1-4, 2023 Y1 - 2023 U6 - https://doi.org/10.1109/SMC53992.2023.10394461 SP - 1000 EP - 1007 ER - TY - CHAP A1 - Münch, Maximilian A1 - Heilig, Simon A1 - Väth, Philipp A1 - Schleif, Frank-Michael T1 - Scalable embedding of multiple perspectives for indefinite life-science data analysis T2 - IEEE Symposium Series on Computational Intelligence, SSCI 2021, Orlando, FL, USA, December 5-7, 2021 Y1 - 2021 U6 - https://doi.org/10.1109/SSCI50451.2021.9659914 SP - 1 EP - 8 ER - TY - CHAP A1 - Raab, Christoph A1 - Väth, Philipp A1 - Meier, Peter A1 - Schleif, Frank-Michael ED - Ishikawa, Hiroshi ED - Liu, Cheng-Lin ED - Pajdla, Tomás ED - Shi, Jianbo T1 - Bridging Adversarial and Statistical Domain Transfer via Spectral Adaptation Networks T2 - Computer Vision - ACCV 2020 - 15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 - December 4, 2020, Revised Selected Papers, Part III Y1 - 2020 U6 - https://doi.org/10.1007/978-3-030-69535-4_28 SP - 457 EP - 473 ER -