File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-01240-3_17
- Scopus: eid_2-s2.0-85055131955
- WOS: WOS:000594233000017
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: PSANet: Point-wise spatial attention network for scene parsing
Title | PSANet: Point-wise spatial attention network for scene parsing |
---|---|
Authors | |
Keywords | Point-wise spatial attention Scene parsing Semantic segmentation Bi-direction information flow Adaptive context aggregation |
Issue Date | 2018 |
Publisher | Springer. |
Citation | 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Ferrari, V, Hebert, M, Sminchisescu, C, Weiss, Y (Eds.), Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part IX, p. 270-286. Cham: Springer, 2018 How to Cite? |
Abstract | We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes. In this paper, we propose the point-wise spatial attention network (PSANet) to relax the local neighborhood constraint. Each position on the feature map is connected to all the other ones through a self-adaptively learned attention mask. Moreover, information propagation in bi-direction for scene parsing is enabled. Information at other positions can be collected to help the prediction of the current position and vice versa, information at the current position can be distributed to assist the prediction of other ones. Our proposed approach achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality. |
Persistent Identifier | http://hdl.handle.net/10722/303867 |
ISBN | |
ISSN | 2020 SCImago Journal Rankings: 0.249 |
ISI Accession Number ID | |
Series/Report no. | Lecture Notes in Computer Science ; 11213 Image Processing, Computer Vision, Pattern Recognition, and Graphics ; 11213 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhao, Hengshuang | - |
dc.contributor.author | Zhang, Yi | - |
dc.contributor.author | Liu, Shu | - |
dc.contributor.author | Shi, Jianping | - |
dc.contributor.author | Loy, Chen Change | - |
dc.contributor.author | Lin, Dahua | - |
dc.contributor.author | Jia, Jiaya | - |
dc.date.accessioned | 2021-09-15T08:26:10Z | - |
dc.date.available | 2021-09-15T08:26:10Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Ferrari, V, Hebert, M, Sminchisescu, C, Weiss, Y (Eds.), Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part IX, p. 270-286. Cham: Springer, 2018 | - |
dc.identifier.isbn | 9783030012397 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/303867 | - |
dc.description.abstract | We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes. In this paper, we propose the point-wise spatial attention network (PSANet) to relax the local neighborhood constraint. Each position on the feature map is connected to all the other ones through a self-adaptively learned attention mask. Moreover, information propagation in bi-direction for scene parsing is enabled. Information at other positions can be collected to help the prediction of the current position and vice versa, information at the current position can be distributed to assist the prediction of other ones. Our proposed approach achieves top performance on various competitive scene parsing datasets, including ADE20K, PASCAL VOC 2012 and Cityscapes, demonstrating its effectiveness and generality. | - |
dc.language | eng | - |
dc.publisher | Springer. | - |
dc.relation.ispartof | Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part IX | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 11213 | - |
dc.relation.ispartofseries | Image Processing, Computer Vision, Pattern Recognition, and Graphics ; 11213 | - |
dc.subject | Point-wise spatial attention | - |
dc.subject | Scene parsing | - |
dc.subject | Semantic segmentation | - |
dc.subject | Bi-direction information flow | - |
dc.subject | Adaptive context aggregation | - |
dc.title | PSANet: Point-wise spatial attention network for scene parsing | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-030-01240-3_17 | - |
dc.identifier.scopus | eid_2-s2.0-85055131955 | - |
dc.identifier.spage | 270 | - |
dc.identifier.epage | 286 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.isi | WOS:000594233000017 | - |
dc.publisher.place | Cham | - |