Hi-Fi: Hierarchical Feature Integration for Skeleton Detection

TL;DR

This paper introduces Hi-Fi, a hierarchical feature integration CNN architecture that effectively captures multi-scale features for skeleton detection, significantly improving performance over existing methods.

Contribution

The paper proposes a novel hierarchical feature integration mechanism within CNNs, enabling mutual refinement of multi-scale features for improved skeleton detection.

Findings

Outperforms state-of-the-art methods on multiple benchmarks

Effectively fuses features across very different scales

Enhances detection accuracy by capturing both high-level semantics and low-level details

Abstract

In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts, making object skeleton detection a challenging problem. We present a new convolutional neural network (CNN) architecture by introducing a novel hierarchical feature integration mechanism, named Hi-Fi, to address the skeleton detection problem. The proposed CNN-based approach has a powerful multi-scale feature integration ability that intrinsically captures high-level semantics from deeper layers as well as low-level details from shallower layers. % By hierarchically integrating different CNN feature levels with bidirectional guidance, our approach (1) enables mutual refinement across features of different levels, and (2) possesses the strong ability to capture both rich object context and high-resolution details. Experimental results show that our method significantly outperforms the state-of-the-art methods in terms of effectively fusing features from very different scales, as evidenced by a considerable performance improvement on several benchmarks.