Zur Kurzanzeige

dc.contributor.author
Li, Xueyi
dc.contributor.author
Zhou, Tianfei
dc.contributor.author
Li, Jianwu
dc.contributor.author
Zhou, Yi
dc.contributor.author
Zhang, Zhaoxiang
dc.date.accessioned
2021-09-07T13:09:57Z
dc.date.available
2021-09-04T16:59:32Z
dc.date.available
2021-09-07T13:09:57Z
dc.date.issued
2021-05-28
dc.identifier.isbn
978-1-57735-866-4
en_US
dc.identifier.issn
2159-5399
dc.identifier.issn
2374-3468
dc.identifier.uri
http://hdl.handle.net/20.500.11850/504089
dc.description.abstract
Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which requires pixel-level annotations. This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths. which can be used for training more accurate segmentation models. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by an efficient co-attention mechanism. Moreover, in order to prevent the model from paying excessive attention to common semantics only, we further propose a graph dropout layer, encouraging the model to learn more accurate and complete object responses. The whole network is end-to-end trainable by iterative message passing, which propagates interaction cues over the images to progressively improve the performance. We conduct experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. Our code is available at: https://github.com/Lixy1997/Group-WSSS.
en_US
dc.language.iso
en
en_US
dc.publisher
AAAI
dc.subject
Segmentation
en_US
dc.subject
Scene analysis & understanding
en_US
dc.subject
Applications
en_US
dc.subject
Other Foundations of Computer Vision
en_US
dc.title
Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
en_US
dc.type
Conference Paper
dc.date.published
2021-05-18
ethz.journal.title
Proceedings of the AAAI Conference on Artificial Intelligence
ethz.journal.volume
35
en_US
ethz.journal.issue
3
en_US
ethz.pages.start
1984
en_US
ethz.pages.end
1992
en_US
ethz.event
35th AAAI Conference on Artificial Intelligence (AAAI 2021)
ethz.event.location
Online
ethz.event.date
February 2-9, 2021
ethz.identifier.wos
ethz.publication.place
Palo Alto, CA
ethz.publication.status
published
en_US
ethz.identifier.url
https://ojs.aaai.org/index.php/AAAI/article/view/16294
ethz.date.deposited
2021-09-04T17:00:31Z
ethz.source
WOS
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.installDate
2021-09-07T13:10:04Z
ethz.rosetta.lastUpdated
2024-02-02T14:39:39Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Group-Wise%20Semantic%20Mining%20for%20Weakly%20Supervised%20Semantic%20Segmentation&rft.jtitle=Proceedings%20of%20the%20AAAI%20Conference%20on%20Artificial%20Intelligence&rft.date=2021-05-28&rft.volume=35&rft.issue=3&rft.spage=1984&rft.epage=1992&rft.issn=2159-5399&2374-3468&rft.au=Li,%20Xueyi&Zhou,%20Tianfei&Li,%20Jianwu&Zhou,%20Yi&Zhang,%20Zhaoxiang&rft.isbn=978-1-57735-866-4&rft.genre=proceeding&
 Printexemplar via ETH-Bibliothek suchen

Dateien zu diesem Eintrag

DateienGrößeFormatIm Viewer öffnen

Zu diesem Eintrag gibt es keine Dateien.

Publikationstyp

Zur Kurzanzeige