ProMask: Probability Mask for Skeleton Detection

TL;DR

ProMask introduces a novel skeleton detection model using probability masks and a vector router, significantly improving accuracy on challenging datasets by explicitly encoding skeletons and dynamically adjusting predictions.

Contribution

The paper proposes ProMask, a new skeleton detection approach combining probability masks and a vector router, providing explicit skeleton encoding and dynamic position adjustment.

Findings

ProMask outperforms state-of-the-art methods on benchmark datasets.

ProMask achieves 6.2% higher accuracy than DeepFlux on SYM-PASCAL.

The method is simple to implement, requiring about 10 lines of code.

Abstract

Detecting object skeletons in natural images presents challenging, due to varied object scales, the complexity of backgrounds and various noises. The skeleton is a highly compressing shape representation, which can bring some essential advantages but cause the difficulties of detection. This skeleton line occupies a rare proportion of an image and is overly sensitive to spatial position. Inspired by these issues, we propose the ProMask, which is a novel skeleton detection model. The ProMask includes the probability mask and vector router. The skeleton probability mask representation explicitly encodes skeletons with segmentation signals, which can provide more supervised information to learn and pay more attention to ground-truth skeleton pixels. Moreover, the vector router module possesses two sets of orthogonal basis vectors in a two-dimensional space, which can dynamically adjust the predicted skeleton position. We evaluate our method on the well-known skeleton datasets, realizing the better performance than state-of-the-art approaches. Especially, ProMask significantly outperforms the competitive DeepFlux by 6.2% on the challenging SYM-PASCAL dataset. We consider that our proposed skeleton probability mask could serve as a solid baseline for future skeleton detection, since it is very effective and it requires about 10 lines of code.