activity
20182022
most citedExploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation

2 citations · 3 across the 5 of their papers we have counts for

collaborators

17 papers

cs.CV2022

Self-Supervised Road Layout Parsing with Graph Auto-Encoding

Chenyang Lu, Gijs Dubbelman

Aiming for higher-level scene understanding, this work presents a neural network approach that takes a road-layout map in bird's-eye-view as input, and predicts a human-interpretab…

cs.LG2021

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…

cs.CV20212 cited

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…

cs.CV2021

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…

cs.CV20201 cited

Image-Graph-Image Translation via Auto-Encoding

Chenyang Lu, Gijs Dubbelman

This work presents the first convolutional neural network that learns an image-to-graph translation task without needing external supervision. Obtaining graph representations of im…

cs.CV2020

Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding

Panagiotis Meletis, Xiaoxiao Wen, Chenyang Lu +2

In this technical report, we present two novel datasets for image scene understanding. Both datasets have annotations compatible with panoptic segmentation and additionally they ha…