Next Article in Journal
Quad-Band Rectenna for Ambient Radio Frequency (RF) Energy Harvesting
Previous Article in Journal
Blind Watermarking of Color Medical Images Using Hadamard Transform and Fractional-Order Moments
Article

Inter-Level Feature Balanced Fusion Network for Street Scene Segmentation

1
School of Electronic Information, Wuhan University, Wuhan 430072, China
2
National Engineering Laboratory for Risk Perception and Prevention (NEL-RPP), Beijing 100041, China
*
Author to whom correspondence should be addressed.
Academic Editor: Jianxin Li
Sensors 2021, 21(23), 7844; https://doi.org/10.3390/s21237844 (registering DOI)
Received: 13 October 2021 / Revised: 18 November 2021 / Accepted: 19 November 2021 / Published: 25 November 2021
Semantic segmentation, as a pixel-level recognition task, has been widely used in a variety of practical scenes. Most of the existing methods try to improve the performance of the network by fusing the information of high and low layers. This kind of simple concatenation or element-wise addition will lead to the problem of unbalanced fusion and low utilization of inter-level features. To solve this problem, we propose the Inter-Level Feature Balanced Fusion Network (IFBFNet) to guide the inter-level feature fusion towards a more balanced and effective direction. Our overall network architecture is based on the encoder–decoder architecture. In the encoder, we use a relatively deep convolution network to extract rich semantic information. In the decoder, skip-connections are added to connect and fuse low-level spatial features to restore a clearer boundary expression gradually. We add an inter-level feature balanced fusion module to each skip connection. Additionally, to better capture the boundary information, we added a shallower spatial information stream to supplement more spatial information details. Experiments have proved the effectiveness of our module. Our IFBFNet achieved a competitive performance on the Cityscapes dataset with only finely annotated data used for training and has been greatly improved on the baseline network. View Full-Text
Keywords: semantic segmentation; encoder–decoder; feature balanced fusion; Cityscapes semantic segmentation; encoder–decoder; feature balanced fusion; Cityscapes
Show Figures

Figure 1

MDPI and ACS Style

Li, D.; Fan, C.; Zou, L.; Zuo, Q.; Jiang, H.; Liu, Y. Inter-Level Feature Balanced Fusion Network for Street Scene Segmentation. Sensors 2021, 21, 7844. https://doi.org/10.3390/s21237844

AMA Style

Li D, Fan C, Zou L, Zuo Q, Jiang H, Liu Y. Inter-Level Feature Balanced Fusion Network for Street Scene Segmentation. Sensors. 2021; 21(23):7844. https://doi.org/10.3390/s21237844

Chicago/Turabian Style

Li, Dongqian, Cien Fan, Lian Zou, Qi Zuo, Hao Jiang, and Yifeng Liu. 2021. "Inter-Level Feature Balanced Fusion Network for Street Scene Segmentation" Sensors 21, no. 23: 7844. https://doi.org/10.3390/s21237844

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop