10 citations · 11 across the 7 of their papers we have counts for
8 papers · 1 filter
Orbis 2: A Hierarchical World Model for Driving
Sudhanshu Mittal, Arian Mousakhan, Silvio Galesso +4
Current world models operate at a single level of abstraction, with most prioritizing perceptual fidelity while lacking the spatial reasoning and semantic understanding required fo…
Orbis: Overcoming Challenges of Long-Horizon Prediction in Driving World Models
Arian Mousakhan, Sudhanshu Mittal, Silvio Galesso +2
Existing world models for autonomous driving struggle with long-horizon generation and generalization to challenging scenarios. In this work, we develop a model using simple design…
Detect, Classify, Act: Categorizing Industrial Anomalies with Multi-Modal Large Language Models
Sassan Mokhtar, Arian Mousakhan, Silvio Galesso +2
Recent advances in visual industrial anomaly detection have demonstrated exceptional performance in identifying and segmenting anomalous regions while maintaining fast inference sp…
Diffusion for Out-of-Distribution Detection on Road Scenes and Beyond
Silvio Galesso, Philipp Schröppel, Hssan Driss +1
In recent years, research on out-of-distribution (OoD) detection for semantic segmentation has mainly focused on road scenes -- a domain with a constrained amount of semantic diver…
Far Away in the Deep Space: Dense Nearest-Neighbor-Based Out-of-Distribution Detection
Silvio Galesso, Max Argus, Thomas Brox
The key to out-of-distribution detection is density estimation of the in-distribution data or of its feature representations. This is particularly challenging for dense anomaly det…
Probing Contextual Diversity for Dense Out-of-Distribution Detection
Silvio Galesso, Maria Alejandra Bravo, Mehdi Naouar +1
Detection of out-of-distribution (OoD) samples in the context of image classification has recently become an area of interest and active study, along with the topic of uncertainty…
Essentials for Class Incremental Learning
Sudhanshu Mittal, Silvio Galesso, Thomas Brox
Contemporary neural networks are limited in their ability to learn from evolving streams of training data. When trained sequentially on new or evolving tasks, their accuracy drops…
Uncertainty Estimates and Multi-Hypotheses Networks for Optical Flow
Eddy Ilg, Özgün Çiçek, Silvio Galesso +4
Optical flow estimation can be formulated as an end-to-end supervised learning problem, which yields estimates with a superior accuracy-runtime tradeoff compared to alternative met…