Episodic CAMN: Contextual Attention-Based Memory Networks with Iterative Feedback for Scene Labeling
Abstract
Scene labeling can be seen as a sequence-sequence prediction task (pixels-labels), and it is quite important to leverage relevant context to enhance the performance of pixel classification. In this paper, we introduce an episodic attention-based memory network to achieve the goal. We present a unified framework that mainly consists of a Convolutional Neural Network (CNN), specifically, Fully Convolutional Network (FCN) and an attention-based memory module with feedback connections to perform context selection and refinement. The full model produces context-aware representation for each target patch by aggregating the activated context and its original local representation produced by the convolution layers. We evaluate our model on PASCAL Context, SIFT Flow and PASCAL VOC 2011 datasets and achieve competitive results to other state-of-the-art methods in scene labeling.
Cite
Text
Abdulnabi et al. "Episodic CAMN: Contextual Attention-Based Memory Networks with Iterative Feedback for Scene Labeling." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.665Markdown
[Abdulnabi et al. "Episodic CAMN: Contextual Attention-Based Memory Networks with Iterative Feedback for Scene Labeling." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/abdulnabi2017cvpr-episodic/) doi:10.1109/CVPR.2017.665BibTeX
@inproceedings{abdulnabi2017cvpr-episodic,
title = {{Episodic CAMN: Contextual Attention-Based Memory Networks with Iterative Feedback for Scene Labeling}},
author = {Abdulnabi, Abrar H. and Shuai, Bing and Winkler, Stefan and Wang, Gang},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2017},
doi = {10.1109/CVPR.2017.665},
url = {https://mlanthology.org/cvpr/2017/abdulnabi2017cvpr-episodic/}
}