Context Attention Network for Skeleton Extraction

TL;DR

This paper introduces CANet, an attention-based model that leverages context information for skeleton extraction, achieving state-of-the-art results with fewer training images and no ensemble.

Contribution

The paper proposes a novel Context Attention Network (CANet) that effectively utilizes context information within a UNet architecture for skeleton extraction.

Findings

Achieved 0.8507 F1 score on the Pixel SkelNetOn dataset.

Ranked 1st in the Pixel SkelNetOn Competition.

Effective with only 80% of training data without model ensemble.

Abstract

Skeleton extraction is a task focused on providing a simple representation of an object by extracting the skeleton from the given binary or RGB image. In recent years many attractive works in skeleton extraction have been made. But as far as we know, there is little research on how to utilize the context information in the binary shape of objects. In this paper, we propose an attention-based model called Context Attention Network (CANet), which integrates the context extraction module in a UNet architecture and can effectively improve the ability of network to extract the skeleton pixels. Meanwhile, we also use some novel techniques including distance transform, weight focal loss to achieve good results on the given dataset. Finally, without model ensemble and with only 80% of the training images, our method achieves 0.822 F1 score during the development phase and 0.8507 F1 score during the final phase of the Pixel SkelNetOn Competition, ranking 1st place on the leaderboard.