no code implementations • 18 Jan 2023 • Panagiotis Meletis, Gijs Dubbelman
We explore semantic segmentation beyond the conventional, single-dataset homogeneous training and bring forward the problem of Heterogeneous Training of Semantic Segmentation (HTSS).
no code implementations • 16 Jan 2022 • Panagiotis Meletis
Motivated by memory and computation efficiency requirements, in Chapter 5, we rethink simultaneous training on heterogeneous datasets and propose a universal semantic segmentation framework.
1 code implementation • 14 Jul 2021 • Ariyan Bighashdel, Panagiotis Meletis, Pavol Jancura, Gijs Dubbelman
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' demonstrations.
no code implementations • 10 Jul 2021 • Jake Rap, Panagiotis Meletis
In this paper, the task of video panoptic segmentation is studied and two different methods to solve the task will be proposed.
1 code implementation • CVPR 2021 • Daan de Geus, Panagiotis Meletis, Chenyang Lu, Xiaoxiao Wen, Gijs Dubbelman
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 unifies the tasks of scene parsing and part parsing.
Ranked #2 on Image Segmentation on Pascal Panoptic Parts
4 code implementations • 16 Apr 2020 • Panagiotis Meletis, Xiaoxiao Wen, Chenyang Lu, Daan de Geus, Gijs Dubbelman
In this technical report, we present two novel datasets for image scene understanding.
no code implementations • 9 Oct 2019 • Daan de Geus, Panagiotis Meletis, Gijs Dubbelman
For lower resolutions of the Cityscapes dataset and for the Pascal VOC dataset, FPSNet runs at 22 and 35 frames per second, respectively.
no code implementations • 16 Jul 2019 • Panagiotis Meletis, Rob Romijnders, Gijs Dubbelman
Training convolutional networks for semantic segmentation with strong (per-pixel) and weak (per-bounding-box) supervision requires a large amount of weakly labeled data.
1 code implementation • 8 Mar 2019 • Panagiotis Meletis, Gijs Dubbelman
We collect street scene images and weak labels from the immense Open Images dataset to generate the OpenScapes dataset, and we use this novel dataset to increase segmentation performance on two established per-pixel labeled datasets, Cityscapes and Vistas.
1 code implementation • 7 Feb 2019 • Daan de Geus, Panagiotis Meletis, Gijs Dubbelman
Our network is evaluated on two street scene datasets: Cityscapes and Mapillary Vistas.
no code implementations • 14 Sep 2018 • Rob Romijnders, Panagiotis Meletis, Gijs Dubbelman
We show that conventional normalization layers worsen the performance of current Unsupervised Adversarial Domain Adaption (UADA), which is a method to improve network performance on unlabeled datasets and the focus of our research.
no code implementations • CoRR 2019 • Daan de Geus, Panagiotis Meletis, Gijs Dubbelman
For instance segmentation, a Mask R-CNN type of architecture is used, while the semantic segmentation branch is augmented with a Pyramid Pooling Module.
Ranked #11 on Panoptic Segmentation on Mapillary val
2 code implementations • 15 Mar 2018 • Panagiotis Meletis, Gijs Dubbelman
We propose a convolutional network with hierarchical classifiers for per-pixel semantic segmentation, which is able to be trained on multiple, heterogeneous datasets and exploit their semantic hierarchy.
Ranked #5 on Semantic Segmentation on KITTI Semantic Segmentation