Fully convolutional networks for semantic segmentation
Citations
10,120 citations
9,803 citations
Cites background from "Fully convolutional networks for se..."
...In the next section, we review related work on deep classification nets, FCNs, and recent approaches to semantic segmentation using convnets....
[...]
...In contemporary work Hariharan et al. [18] also use multiple layers in their hybrid model for semantic segmentation....
[...]
...Finally, we demonstrate state-of-the-art results on PASCAL VOC 2011-2, NYUDv2, and SIFT Flow....
[...]
8,730 citations
Cites background or methods from "Fully convolutional networks for se..."
...Although this is not the first paper to introduce learned upsampling paths in convolutional neural networks (e.g. Long et al., 2015 ), the authors combined it with so called skip-connections to directly connect opposing contracting and expanding convolutional layers....
[...]
...Long et al. (2015)), the authors combined it with so called skip-connections to directly connect opposing contracting and expanding convolutional layers....
[...]
...‘Shift-and-stitch’ ( Long et al., 2015 ) is one of several methods proposed to prevent this de- crease in resolution....
[...]
...’Shift-and-stitch’ (Long et al., 2015) is one of several methods proposed to prevent this decrease in resolution....
[...]
7,556 citations
7,547 citations
References
73,978 citations
49,914 citations
22,840 citations
21,729 citations
17,693 citations
"Fully convolutional networks for se..." refers methods in this paper
...Although performing this transformation naı̈vely increases the cost by a factor of f, there is a well-known trick for efficiently producing identical results [13, 32] known to the wavelet community as the à trous algorithm [27]....
[...]