Semantic Segmentation on Multiple Visual Domains
release_t7zwcdae7ze2zfcqoukuabty5i
by
Floris Naber
2021
Abstract
Semantic segmentation models only perform well on the domain they are trained
on and datasets for training are scarce and often have a small label-spaces,
because the pixel level annotations required are expensive to make. Thus
training models on multiple existing domains is desired to increase the output
label-space. Current research shows that there is potential to improve accuracy
across datasets by using multi-domain training, but this has not yet been
successfully extended to datasets of three different non-overlapping domains
without manual labelling. In this paper a method for this is proposed for the
datasets Cityscapes, SUIM and SUN RGB-D, by creating a label-space that spans
all classes of the datasets. Duplicate classes are merged and discrepant
granularity is solved by keeping classes separate. Results show that accuracy
of the multi-domain model has higher accuracy than all baseline models
together, if hardware performance is equalized, as resources are not limitless,
showing that models benefit from additional data even from domains that have
nothing in common.
In text/plain
format
Archived Files and Locations
application/pdf 2.1 MB
file_34w6fkamrbdqrcgeu7mmzbnsyi
|
arxiv.org (repository) web.archive.org (webarchive) |
2107.04326v1
access all versions, variants, and formats of this works (eg, pre-prints)