Conference item
Dense decoder shortcut connections for single-pass semantic segmentation
- Abstract:
-
We propose a novel end-to-end trainable, deep, encoder-decoder architecture for single-pass semantic segmentation. Our approach is based on a cascaded architecture with feature-level long-range skip connections. The encoder incorporates the structure of ResNeXt's residual building blocks and adopts the strategy of repeating a building block that aggregates a set of transformations with the same topology. The decoder features a novel architecture, consisting of blocks, that (i) capture context...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Bibliographic Details
- Publisher:
- Institute for Electrical and Electronics Engineers Publisher's website
- Pages:
- 6596-6605
- Host title:
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- Publication date:
- 2018-12-17
- Event title:
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Event location:
- Salt Lake City, UT, USA
- Event website:
- https://cvpr2018.thecvf.com/
- Event start date:
- 2018-06-18T00:00:00Z
- Event end date:
- 2018-06-23T00:00:00Z
- DOI:
- EISBN:
-
9781538664209
- EISSN:
-
2575-7075
- ISSN:
-
1063-6919
- Source identifiers:
-
953152
- ISBN:
- 9781538664216
Item Description
- Language:
- English
- Deposit date:
- 2018-12-18
Terms of use
- Copyright holder:
- Institute of Electrical and Electronics Engineers
- Copyright date:
- 2018
- Rights statement:
- © 2018 IEEE.
- Notes:
-
This paper was presented at the Conference on Computer Vision and Pattern Recognition
(CVPR 2018), June 18-23, 2018, Salt Lake City, UT, USA. This is the accepted manuscript version of the article. The final version is available online from IEEE at: 10.1109/CVPR.2018.00690
If you are the owner of this record, you can report an update to it here: Report update to this record