Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs

By Wei Shen, Kai Zhao, Yuan Jiang, Yan Wang, Zhijiang Zhang, Xiang Bai. 2016

106 citations recorded by the source corpus.

Object skeleton is a useful cue for object detection, complementary to the object contour, as it provides a structural representation to describe the relationship among object parts. While object skeleton extraction in natural images is a very challenging problem, as it requires the extractor to be able to capture both local and global image context to determine the intrinsic scale of each skeleton pixel. Existing methods rely on per-pixel based multi-scale feature computation, which results in difficult modeling and high time consumption. In this paper, we present a fully convolutional network with multiple scale-associated side outputs to address this problem. By observing the relationship between the receptive field sizes of the sequential stages in the network and the skeleton scales they can capture, we introduce a scale-associated side output to each stage. We impose supervision to different stages by guiding the scale-associated side outputs toward groundtruth skeletons of different scales. The responses of the multiple scaleassociated side outputs are then fused in a scale-specific way to localize skeleton pixels with multiple scales effectively. Our method achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Holistically-Nested Edge Detection (2015, background): “2016); scale-sensitive deep supervision is introduced in (Shen et al. 2016) for object skeleton extraction.”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, background): “…only considering works that apply to a single, static image we can indicatively list successes of CNNs in superresolution [24], colorization [55], boundary detection [6,28,49,107], symmetry detection [91], interest point detection [109], image descriptors [35, 92, 110], surface Input Boundaries”
Recent Advances in Deep Learning for Object Detection (2019, background): “ject detection such as vehicle detection [227–229] , traffic-sign de1759 tection [230,231] and skeleton detection [232,233] .”
Beyond Planar Symmetry: Modeling Human Perception of Reflection and Rotation Symmetries in the Wild (2017, methodology): “Reflection Symmetry Detection Proposed Sym-NETs Original Image Ground Truth Loy & Eklundh [46] MIL [67] SRF [63] FSDS [59] Sym-VGG Sym-ResNet”
Traffic sign detection and recognition using fully convolutional network guided proposals (2016, background): “Recently, FCN has achieved advanced performance on object segmentation and edge detection [18,52,53].”