176 citations · 274 across the 36 of their papers we have counts for
3 papers · 1 filter
Deep Adaptive Multi-Intention Inverse Reinforcement Learning
Ariyan Bighashdel, Panagiotis Meletis, Pavol Jancura +1
This paper presents a deep Inverse Reinforcement Learning (IRL) framework that can learn an a priori unknown number of nonlinear reward functions from unlabeled experts' demonstrat…
Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation
Fabrizio J. Piva, Gijs Dubbelman
We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We f…
Part-aware Panoptic Segmentation
Daan de Geus, Panagiotis Meletis, Chenyang Lu +2
In this work, we introduce the new scene understanding task of Part-aware Panoptic Segmentation (PPS), which aims to understand a scene at multiple levels of abstraction, and unifi…