• Corpus ID: 246036085

Towards holistic scene understanding: Semantic segmentation and beyond

@article{Meletis2022TowardsHS,
  title={Towards holistic scene understanding: Semantic segmentation and beyond},
  author={Panagiotis Meletis},
  journal={ArXiv},
  year={2022},
  volume={abs/2201.07734}
}
This dissertation addresses visual scene understanding and enhances segmentation performance and generalization, training efficiency of networks, and holistic understanding. First, we investigate semantic segmentation in the context of street scenes and train semantic segmentation networks on combinations of various datasets. In Chapter 2 we design a framework of hierarchical classifiers over a single convolutional backbone, and train it end-to-end on a combination of pixel-labeled datasets…