Loading...
Please wait, while we are loading the content...
Similar Documents
Circle-U-Net: An Efficient Architecture for Semantic Segmentation
| Content Provider | MDPI |
|---|---|
| Author | Ajith, V. Sun, Feng Yang, Guanci Zhang, Ansi Zhang, Yiyun |
| Copyright Year | 2021 |
| Description | State-of-the-art semantic segmentation methods rely too much on complicated deep networks and thus cannot train efficiently. This paper introduces a novel Circle-U-Net architecture that exceeds the original U-Net on several standards. The proposed model includes circle connect layers, which is the backbone of ResUNet-a architecture. The model possesses a contracting part with residual bottleneck and circle connect layers that capture context and expanding paths, with sampling layers and merging layers for a pixel-wise localization. The results of the experiment show that the proposed Circle-U-Net achieves an improved accuracy of 5.6676%, 2.1587% IoU (Intersection of union, IoU) and can detect 67% classes greater than U-Net, which is better than current results. |
| Starting Page | 159 |
| e-ISSN | 19994893 |
| DOI | 10.3390/a14060159 |
| Journal | Algorithms |
| Issue Number | 6 |
| Volume Number | 14 |
| Language | English |
| Publisher | MDPI |
| Publisher Date | 2021-05-21 |
| Access Restriction | Open |
| Subject Keyword | Algorithms Transportation Science and Technology U-net Deep Learning Object Segmentation Attention Mechanism Convolutional Neural Network (cnn) |
| Content Type | Text |
| Resource Type | Article |
