Home | << 1 >> |
![]() |
Record | Links | |||||
---|---|---|---|---|---|---|
Author ![]() |
Carlo Gatta; Adriana Romero; Joost Van de Weijer |
![]() ![]() ![]() ![]() |
||||
Title | Unrolling loopy top-down semantic feedback in convolutional deep networks | Type | Conference Article | |||
Year | 2014 | Publication | Workshop on Deep Vision: Deep Learning for Computer Vision | Abbreviated Journal | ||
Volume | Issue | Pages | 498-505 | |||
Keywords | ||||||
Abstract | In this paper, we propose a novel way to perform top-down semantic feedback in convolutional deep networks for efficient and accurate image parsing. We also show how to add global appearance/semantic features, which have shown to improve image parsing performance in state-of-the-art methods, and was not present in previous convolutional approaches. The proposed method is characterised by an efficient training and a sufficiently fast testing. We use the well known SIFTflow dataset to numerically show the advantages provided by our contributions, and to compare with state-of-the-art image parsing convolutional based approaches. | |||||
Address | Columbus; Ohio; June 2014 | |||||
Corporate Author | Thesis | |||||
Publisher | Place of Publication | Editor | ||||
Language | Summary Language | Original Title | ||||
Series Editor | Series Title | Abbreviated Series Title | ||||
Series Volume | Series Issue | Edition | ||||
ISSN | ISBN | Medium | ||||
Area | Expedition | Conference | CVPRW | |||
Notes | LAMP; MILAB; 601.160; 600.079;CIC | Approved | no | |||
Call Number | Admin @ si @ GRW2014 | Serial | 2490 | |||
Permanent link to this record |