Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation
release_aaclo4aktzg5nb2tm22pjnecjy
by
Daehan Kim, Minseok Seo, Jinsun Park, Dong-Geol Choi
2022
Abstract
In this paper, we introduce source domain subset sampling (SDSS) as a new
perspective of semi-supervised domain adaptation. We propose domain adaptation
by sampling and exploiting only a meaningful subset from source data for
training. Our key assumption is that the entire source domain data may contain
samples that are unhelpful for the adaptation. Therefore, the domain adaptation
can benefit from a subset of source data composed solely of helpful and
relevant samples. The proposed method effectively subsamples full source data
to generate a small-scale meaningful subset. Therefore, training time is
reduced, and performance is improved with our subsampled source data. To
further verify the scalability of our method, we construct a new dataset called
Ocean Ship, which comprises 500 real and 200K synthetic sample images with
ground-truth labels. The SDSS achieved a state-of-the-art performance when
applied on GTA5 to Cityscapes and SYNTHIA to Cityscapes public benchmark
datasets and a 9.13 mIoU improvement on our Ocean Ship dataset over a baseline
model.
In text/plain
format
Archived Files and Locations
application/pdf 11.5 MB
file_36ad54lqozb65a6uacpxv5qs74
|
arxiv.org (repository) web.archive.org (webarchive) |
2205.00312v2
access all versions, variants, and formats of this works (eg, pre-prints)