2022
DOI: 10.1007/s13735-022-00229-6
|View full text |Cite
|
Sign up to set email alerts
|

PDS-Net: A novel point and depth-wise separable convolution for real-time object detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
1

Relationship

1
4

Authors

Journals

citations
Cited by 8 publications
(1 citation statement)
references
References 60 publications
0
1
0
Order By: Relevance
“…This detector has a feature extractor and classification module, which is based on Yolo-v5 [ 21 ]. A fundamental strategy of improving the exactness feature extraction of CNN-based object detectors [ 22 ] is to broaden the receptive field and increase the system’s complexity employing additional layers whereas identifying tiny objects more effectively. Instead, for easier training, we utilized a skip-connections method.…”
Section: Proposed Methodsmentioning
confidence: 99%
“…This detector has a feature extractor and classification module, which is based on Yolo-v5 [ 21 ]. A fundamental strategy of improving the exactness feature extraction of CNN-based object detectors [ 22 ] is to broaden the receptive field and increase the system’s complexity employing additional layers whereas identifying tiny objects more effectively. Instead, for easier training, we utilized a skip-connections method.…”
Section: Proposed Methodsmentioning
confidence: 99%