Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

6
749
0
8

Year Published

2020
2020
2022
2022

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 1,123 publications
(763 citation statements)
references
References 16 publications
6
749
0
8
Order By: Relevance
“…Operating on the range image opens up the use faster FCN architectures. Prioritizing speed, we use a simplified version of ERFNet [26] with Non-bottleneck-1D structure, Downsampler and Deconvolution layers [26,Sec. IIIb].…”
Section: B Deep Learning Tree Segmentationmentioning
confidence: 99%
“…Operating on the range image opens up the use faster FCN architectures. Prioritizing speed, we use a simplified version of ERFNet [26] with Non-bottleneck-1D structure, Downsampler and Deconvolution layers [26,Sec. IIIb].…”
Section: B Deep Learning Tree Segmentationmentioning
confidence: 99%
“…Due to the efficiency of ENet, it can be used for the tasks requiring low latency operations. Efficient Spatial Pyramid Network (ESPNet) [50] and Efficient Residual Factorized Network (ERFNet) [28] are another two efficient real-time semantic segmentation methods, which are faster and more accurate than ENet using the similar number of parameters. In particular, ESPNet makes use of the Efficient Spatial Pyramid module (ESP), which follows the convolution factorization principle that decomposes a standard convolution into a pointwise convolution and a spatial pyramid of atrous convolutions.…”
Section: B Real-time Semantic Segmentation Methodsmentioning
confidence: 99%
“…According to the content of scenes, the dataset is usually annotated into 30 semantic categories. However, like state-of-the-art methods [29], [28], 19 common semantic categories (such as road, car and person) are only used for training and evaluation in our experiments. Besides the 5000 finely annotated images, the Cityscapes dataset also provides additional 20000 images with coarse annotations.…”
Section: A Datasets and Evaluation Metricsmentioning
confidence: 99%
See 1 more Smart Citation
“…Standard [21] n 2 cĉ n × n Group [15] n 2 cĉ/g n × n 1D-factorized [13] 2ncĉ n × n DW [11,12] n 2 c + cĉ n × n DDW [14] n 2 c + cĉ n r × n r our FDDWC 2nc + cĉ n r × n r…”
Section: Convolutional Type Parameters Size Of Receptive Fieldmentioning
confidence: 99%