Soft labelling for semantic segmentation: Bringing coherence to label down-sampling

arXiv:2302.13961v3 Announce Type: replace
Abstract: In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies for the image data and the annotated labels. Such discrepancy leads to mismatches between the down-sampled color and label images. Hence, the training performance significantly decreases as the down-sampling factor increases. In this paper, we bring together the down-sampling strategies for the …

abstract adapt arxiv augmentation cs.cv data image image data labelling labels leads resources sampling segmentation semantic strategies training training data type