Scale-Aware Feature Network for Weakly Supervised Semantic Segmentation

Lian Xu

doi:10.1109/ACCESS.2020.2989331

Return

Scale-Aware Feature Network for Weakly Supervised Semantic Segmentation

2020-01-01

DOI：10.1109/ACCESS.2020.2989331

Original

Save

View PDF

Abstract

En 中文

Weakly supervised semantic segmentation with image-level labels is of great significance since it alleviates the dependency on dense annotations. However, as it relies on image classification networks that are only capable of producing sparse object localization maps, its performance is far behind that of fully supervised semantic segmentation models. Inspired by the successful use of multi-scale features for an improved performance in a wide range of visual tasks, we propose a Scale-Aware Feature Network (SAFN) for generating object localization maps. The proposed SAFN uses an attention module to learn the relative weights of multi-scale features in a modified fully convolutional network with dilated convolutions. This approach leads to efficient enlargements of the receptive fields of view and produces dense object localization maps. Our approach achieves mIoUs of 62.3%and 66.5% on the PASCAL VOC 2012 test set using VGG16 based and ResNet based segmentation models, respectively, outperforming other state-of-the-art methods for the weakly supervised semantic segmentation task.

Keywords:

Semantics

Image segmentation

Visualization

Task analysis

Australia

Training

Electronic mail

Weakly supervised semantic segmentation

attention mechanism

object saliency

multi-scale learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.