PlaneNet: an efficient local feature extraction network
Due to memory and computing resources limitations, deploying convolutional neural networks on embedded and mobile devices is challenging. However, the redundant use of the 1 × 1 convolution in traditional light-weight networks, such as MobileNetV1, has increased the computing time. By utilizing the...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2021-12-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-783.pdf |
| _version_ | 1818461594637565952 |
|---|---|
| author | Bin Lin Houcheng Su Danyang Li Ao Feng Hongxiang Li Jiao Li Kailin Jiang Hongbo Jiang Xinyao Gong Tao Liu |
| author_facet | Bin Lin Houcheng Su Danyang Li Ao Feng Hongxiang Li Jiao Li Kailin Jiang Hongbo Jiang Xinyao Gong Tao Liu |
| author_sort | Bin Lin |
| collection | DOAJ |
| description | Due to memory and computing resources limitations, deploying convolutional neural networks on embedded and mobile devices is challenging. However, the redundant use of the 1 × 1 convolution in traditional light-weight networks, such as MobileNetV1, has increased the computing time. By utilizing the 1 × 1 convolution that plays a vital role in extracting local features more effectively, a new lightweight network, named PlaneNet, is introduced. PlaneNet can improve the accuracy and reduce the numbers of parameters and multiply-accumulate operations (Madds). Our model is evaluated on classification and semantic segmentation tasks. In the classification tasks, the CIFAR-10, Caltech-101, and ImageNet2012 datasets are used. In the semantic segmentation task, PlaneNet is tested on the VOC2012 datasets. The experimental results demonstrate that PlaneNet (74.48%) can obtain higher accuracy than MobileNetV3-Large (73.99%) and GhostNet (72.87%) and achieves state-of-the-art performance with fewer network parameters in both tasks. In addition, compared with the existing models, it has reached the practical application level on mobile devices. The code of PlaneNet on GitHub: https://github.com/LinB203/planenet. |
| first_indexed | 2024-12-14T23:48:38Z |
| format | Article |
| id | doaj.art-d0f649b5096642358e5ed44bfde45dc2 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-14T23:48:38Z |
| publishDate | 2021-12-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-d0f649b5096642358e5ed44bfde45dc22022-12-21T22:43:19ZengPeerJ Inc.PeerJ Computer Science2376-59922021-12-017e78310.7717/peerj-cs.783PlaneNet: an efficient local feature extraction networkBin Lin0Houcheng Su1Danyang Li2Ao Feng3Hongxiang Li4Jiao Li5Kailin Jiang6Hongbo Jiang7Xinyao Gong8Tao Liu9Sichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Science, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaSichuan Agricultural University, College of Information Engineering, Yaan, Sichuan, ChinaDue to memory and computing resources limitations, deploying convolutional neural networks on embedded and mobile devices is challenging. However, the redundant use of the 1 × 1 convolution in traditional light-weight networks, such as MobileNetV1, has increased the computing time. By utilizing the 1 × 1 convolution that plays a vital role in extracting local features more effectively, a new lightweight network, named PlaneNet, is introduced. PlaneNet can improve the accuracy and reduce the numbers of parameters and multiply-accumulate operations (Madds). Our model is evaluated on classification and semantic segmentation tasks. In the classification tasks, the CIFAR-10, Caltech-101, and ImageNet2012 datasets are used. In the semantic segmentation task, PlaneNet is tested on the VOC2012 datasets. The experimental results demonstrate that PlaneNet (74.48%) can obtain higher accuracy than MobileNetV3-Large (73.99%) and GhostNet (72.87%) and achieves state-of-the-art performance with fewer network parameters in both tasks. In addition, compared with the existing models, it has reached the practical application level on mobile devices. The code of PlaneNet on GitHub: https://github.com/LinB203/planenet.https://peerj.com/articles/cs-783.pdfFeature extractionLocal feature fusionefficiencyStrong operabilityReduce redundant |
| spellingShingle | Bin Lin Houcheng Su Danyang Li Ao Feng Hongxiang Li Jiao Li Kailin Jiang Hongbo Jiang Xinyao Gong Tao Liu PlaneNet: an efficient local feature extraction network PeerJ Computer Science Feature extraction Local feature fusion efficiency Strong operability Reduce redundant |
| title | PlaneNet: an efficient local feature extraction network |
| title_full | PlaneNet: an efficient local feature extraction network |
| title_fullStr | PlaneNet: an efficient local feature extraction network |
| title_full_unstemmed | PlaneNet: an efficient local feature extraction network |
| title_short | PlaneNet: an efficient local feature extraction network |
| title_sort | planenet an efficient local feature extraction network |
| topic | Feature extraction Local feature fusion efficiency Strong operability Reduce redundant |
| url | https://peerj.com/articles/cs-783.pdf |
| work_keys_str_mv | AT binlin planenetanefficientlocalfeatureextractionnetwork AT houchengsu planenetanefficientlocalfeatureextractionnetwork AT danyangli planenetanefficientlocalfeatureextractionnetwork AT aofeng planenetanefficientlocalfeatureextractionnetwork AT hongxiangli planenetanefficientlocalfeatureextractionnetwork AT jiaoli planenetanefficientlocalfeatureextractionnetwork AT kailinjiang planenetanefficientlocalfeatureextractionnetwork AT hongbojiang planenetanefficientlocalfeatureextractionnetwork AT xinyaogong planenetanefficientlocalfeatureextractionnetwork AT taoliu planenetanefficientlocalfeatureextractionnetwork |