Hi-Fi: Hierarchical Feature Integration for Skeleton Detection

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.

IJCAI2018

References in corpus (8)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Fully Convolutional Networks for Semantic Segmentation
• Richer Convolutional Features for Edge Detection
• Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
• DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
• Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
• Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs
• SRN: Side-output Residual Network for Object Symmetry Detection in the Wild