Recently, adversarial erasing for weakly-supervised object attention has been
deeply studied due to its capability in localizing integral object regions.
However, such a strategy raises one key problem that attention regions will
gradually expand to non-object regions as training iterations continue, which
significantly decreases the quality of the produced attention maps. To tackle
such an issue as well as promote the quality of object attention, we introduce
a simple yet effective Self-Erasing Network (SeeNet) to prohibit attentions
from spreading to unexpected background regions. In particular, SeeNet
leverages two self-erasing strategies to encourage networks to use reliable
object and background cues for learning to attention. In this way, integral
object regions can be effectively highlighted without including much more
background regions. To test the quality of the generated attention maps, we
employ the mined object regions as heuristic cues for learning semantic
segmentation models. Experiments on Pascal VOC well demonstrate the superiority
of our SeeNet over other state-of-the-art methods.
%0 Generic
%1 citeulike:14659106
%A xxx,
%D 2018
%K adversarial attention code detection head segmentation semisup
%T Self-Erasing Network for Integral Object Attention
%U http://arxiv.org/abs/1810.09821
%X Recently, adversarial erasing for weakly-supervised object attention has been
deeply studied due to its capability in localizing integral object regions.
However, such a strategy raises one key problem that attention regions will
gradually expand to non-object regions as training iterations continue, which
significantly decreases the quality of the produced attention maps. To tackle
such an issue as well as promote the quality of object attention, we introduce
a simple yet effective Self-Erasing Network (SeeNet) to prohibit attentions
from spreading to unexpected background regions. In particular, SeeNet
leverages two self-erasing strategies to encourage networks to use reliable
object and background cues for learning to attention. In this way, integral
object regions can be effectively highlighted without including much more
background regions. To test the quality of the generated attention maps, we
employ the mined object regions as heuristic cues for learning semantic
segmentation models. Experiments on Pascal VOC well demonstrate the superiority
of our SeeNet over other state-of-the-art methods.
@misc{citeulike:14659106,
abstract = {{ Recently, adversarial erasing for weakly-supervised object attention has been
deeply studied due to its capability in localizing integral object regions.
However, such a strategy raises one key problem that attention regions will
gradually expand to non-object regions as training iterations continue, which
significantly decreases the quality of the produced attention maps. To tackle
such an issue as well as promote the quality of object attention, we introduce
a simple yet effective Self-Erasing Network (SeeNet) to prohibit attentions
from spreading to unexpected background regions. In particular, SeeNet
leverages two self-erasing strategies to encourage networks to use reliable
object and background cues for learning to attention. In this way, integral
object regions can be effectively highlighted without including much more
background regions. To test the quality of the generated attention maps, we
employ the mined object regions as heuristic cues for learning semantic
segmentation models. Experiments on Pascal VOC well demonstrate the superiority
of our SeeNet over other state-of-the-art methods.}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/27844026b50d16e0f96afb4d59c1cd4e0/nmatsuk},
citeulike-article-id = {14659106},
citeulike-linkout-0 = {http://arxiv.org/abs/1810.09821},
citeulike-linkout-1 = {http://arxiv.org/pdf/1810.09821},
day = 23,
eprint = {1810.09821},
interhash = {d0dffb6fc9b6e57beca835d38c274782},
intrahash = {7844026b50d16e0f96afb4d59c1cd4e0},
keywords = {adversarial attention code detection head segmentation semisup},
month = oct,
posted-at = {2018-11-28 06:58:43},
priority = {5},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{Self-Erasing Network for Integral Object Attention}},
url = {http://arxiv.org/abs/1810.09821},
year = 2018
}