7 papers
Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models
Venkatesh Thirugnana Sambandham, Torsten Schön
Modern text-to-image (T2I) models amplify harmful societal biases, challenging their ethical deployment. We introduce an inference-time method that reliably mitigates social bias w…
Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies
Megan Smith, Venkatesh Thirugnana Sambandham, Florian Richter +3
Text-to-Image (T2I) generation models have been widely adopted across various industries, yet are criticized for frequently exhibiting societal stereotypes. While a growing body of…
Zwitscherkasten -- DIY Audiovisual bird monitoring
Dominik Blum, Elias Häring, Fabian Jirges +4
This paper presents Zwitscherkasten, a DiY, multimodal system for bird species monitoring using audio and visual data on edge devices. Deep learning models for bioacoustic and imag…
Unlocking Past Information: Temporal Embeddings in Cooperative Bird's Eye View Prediction
Dominik RöÃle, Jeremias Gerner, Klaus Bogenberger +3
Accurate and comprehensive semantic segmentation of Bird's Eye View (BEV) is essential for ensuring safe and proactive navigation in autonomous driving. Although cooperative percep…
UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception
Karthikeyan Chandra Sekaran, Markus Geisler, Dominik RöÃle +6
Recent cooperative perception datasets have played a crucial role in advancing smart mobility applications by enabling information exchange between intelligent agents, helping to o…
Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
Adithya Mohan, Dominik RöÃle, Daniel Cremers +1
Recent advancements in Deep Reinforcement Learning (DRL) have demonstrated its applicability across various domains, including robotics, healthcare, energy optimization, and autono…