.png){kind=icon}
.png){kind=icon}
Return
EFRNet: Efficient Feature Reconstructing Network for Real-Time Scene Parsing
.png){kind=icon}
PRE
AI
DOI：10.1109/TMM.2021.3089422.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we introduce a light-weight and powerful convolutional neural network, termed as efficient feature reconstructing network (EFRNet), for real-time scene parsing. Our key idea is to decompose the process of learning high-resolution representations into two stages: i) bottom-up codebook/coding matrix learning and ii) top-down feature reconstructing. Specifically, the bottom-up process focuses on learning image-specific codewords (codebook) using deep-layer features and generating a coding matrix with the shallow-layer feature map. In the top-down process, the learned codebook and coding matrix are used to rebuild high-resolution features via a lightweight feature reconstructing operator (FRO). In addition, our EFRNet is constructed on a new building block, named efficient adaptive abstraction (EAA) block, to further reduce the overall network parameters and achieve a significant speed up. Extensive experiments are conducted on challenging benchmarks, such as CamVid and Cityscapes. The results show that EFRNet demonstrates state-of-the-art performance with an optimal balance between accuracy and speed.
Keywords:
Image reconstruction
Semantics
Encoding
Feature extraction
Convolutional codes
Real-time systems
Task analysis
Scene parsing
dictionary learning
representation learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.7
Papers:
4.5K
Citations:
2.4W