SiG-DML-P4: Generative and Unsupervised Learning
Thu, 11 Sep, 11:00 - 12:40 Italy Time (UTC +2)
Location: Poster Area D
Session Type: Poster
Session Co-Chairs: Kai Uwe Barthel, HTW Berlin and Peter Eisert, Fraunhofer HHI / HU Berlin
Track: SiG-DML - Signal and Data Analytics for Machine Learning

SiG-DML-P4.1: ANALYSIS OF PSEUDO-LABELING FOR ONLINE SOURCE-FREE UNIVERSAL DOMAIN ADAPTATION
Pascal Schlachter, Jonathan Fuss, Bin Yang, University of Stuttgart, Germany

SiG-DML-P4.2: ACCELERATED IMAGE-AWARE DIFFUSION MODELING
, ; Tanmay Asthana, North Carolina State University, United States; Yufang Bao, Fayetteville State University, United States; Amro Awad, University of Oxford, United Kingdom; Hamid Krim, North Carolina State University, United States

SiG-DML-P4.3: Diffusion Models for Multifractal Texture Synthesis
Kinan Abbas, Patrice Abry, Stephane Roux, CNRS, ENS de Lyon, France

SiG-DML-P4.4: INTEGRATING CONTRACTIVE LOSS IN PROXIMAL POLICY OPTIMIZATION FOR ROBUST DECISION-MAKING
Michail Dadopoulos, Loukia Avramelou, Nikolaos Passalis, Anastasios Tefas, Aristotle University of Thessaloniki, Greece

SiG-DML-P4.5: DIFFUSION-BASED FORECASTING FOR UNCERTAINTY-AWARE MODEL PREDICTIVE CONTROL
Stelios Zarifis, Athena Research Center, Greece; Ioannis Kordonis, National Technical University of Athens, Greece; Petros Maragos, Athena Research Center, Greece

SiG-DML-P4.6: MAXIMUM A POSTERIORI TRAINING OF DIFFUSION MODELS FOR IMAGE RESTORATION
Samuel Willingham, Mårten Sjöström, Mid Sweden University, Sweden; Christine Guillemot, National Institute for Research in Digital Science and Technology, France

SiG-DML-P4.7: BEYOND CLASSIFICATION: EVALUATING DIFFUSION DENOISED SMOOTHING FOR SECURITY-UTILITY TRADE OFF
Yury Belousov, Brian Pulfer, Vitaliy Kinakh, Slava Voloshynovskiy, University of Geneva, Switzerland

SiG-DML-P4.8: PERMUTATION LEARNING WITH ONLY N PARAMETERS: FROM SOFTSORT TO SELF-ORGANIZING GAUSSIANS
Kai Uwe Barthel, HTW Berlin, Germany; Florian Barthel, Peter Eisert, Fraunhofer HHI / HU Berlin, Germany