.png){kind=icon}
Return
Semantic Segmentation With Context Encoding and Multi-Path Decoding
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2019.2962685.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Semantic image segmentation aims to classify every pixel of a scene image to one of many classes. It implicitly involves object recognition, localization, and boundary delineation. In this paper, we propose a segmentation network called CGBNet to enhance the segmentation performance by context encoding and multi-path decoding. We first propose a context encoding module that generates context-contrasted local feature to make use of the informative context and the discriminative local information. This context encoding module greatly improves the segmentation performance, especially for inconspicuous objects. Furthermore, we propose a scale-selection scheme to selectively fuse the segmentation results from different-scales of features at every spatial position. It adaptively selects appropriate score maps from rich scales of features. To improve the segmentation performance results at boundary, we further propose a boundary delineation module that encourages the location-specific very-low-level features near the boundaries to take part in the final prediction and suppresses them far from the boundaries. The proposed segmentation network achieves very competitive performance in terms of all three different evaluation metrics consistently on the six popular scene segmentation datasets, Pascal Context, SUN-RGBD, Sift Flow, COCO Stuff, ADE20K, and Cityscapes.
Keywords:
Semantic segmentation
context encoding
gated sum
boundary delineation refinement
deep learning
CGBNet
convolutional neural networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSaveShareSaveShareSave
View more