|
|
|
|
| LEADER |
01000caa a22002652c 4500 |
| 001 |
NLM358339235 |
| 003 |
DE-627 |
| 005 |
20250304222157.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
231226s2023 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1016/j.neucom.2022.12.024
|2 doi
|
| 028 |
5 |
2 |
|a pubmed25n1194.xml
|
| 035 |
|
|
|a (DE-627)NLM358339235
|
| 035 |
|
|
|a (NLM)37332394
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Salehi, Ali
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a DDCNet
|b Deep Dilated Convolutional Neural Network for Dense Prediction
|
| 264 |
|
1 |
|c 2023
|
| 336 |
|
|
|a Text
|b txt
|2 rdacontent
|
| 337 |
|
|
|a ƒaComputermedien
|b c
|2 rdamedia
|
| 338 |
|
|
|a ƒa Online-Ressource
|b cr
|2 rdacarrier
|
| 500 |
|
|
|a Date Revised 20.09.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designed for these problems have been successful. A sufficiently larger effective receptive field (ERF) and a higher resolution of spatial features within a network are essential for providing higher-resolution dense estimates. In this work, we present a systemic approach to design network architectures that can provide a larger receptive field while maintaining a higher spatial feature resolution. To achieve a larger ERF, we utilized dilated convolutional layers. By aggressively increasing dilation rates in the deeper layers, we were able to achieve a sufficiently larger ERF with a significantly fewer number of trainable parameters. We used optical flow estimation problem as the primary benchmark to illustrate our network design strategy. The benchmark results (Sintel, KITTI, and Middlebury) indicate that our compact networks can achieve comparable performance in the class of lightweight networks
|
| 650 |
|
4 |
|a Journal Article
|
| 650 |
|
4 |
|a Dense prediction
|
| 650 |
|
4 |
|a compact network
|
| 650 |
|
4 |
|a dilated convolution
|
| 650 |
|
4 |
|a gridding artifact
|
| 650 |
|
4 |
|a network receptive field
|
| 650 |
|
4 |
|a optical flow estimation
|
| 700 |
1 |
|
|a Balasubramanian, Madhusudhanan
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t Neurocomputing
|d 1998
|g 523(2023) vom: 28. Feb., Seite 116-129
|w (DE-627)NLM098202456
|x 0925-2312
|7 nnas
|
| 773 |
1 |
8 |
|g volume:523
|g year:2023
|g day:28
|g month:02
|g pages:116-129
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1016/j.neucom.2022.12.024
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 523
|j 2023
|b 28
|c 02
|h 116-129
|