DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images

@article{Shen2017DeepSkeletonLM,
  title={DeepSkeleton: Learning Multi-Task Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images},
  author={Wei Shen and Kai Zhao and Yuan Jiang and Yan Wang and Xiang Bai and Alan Loddon Yuille},
  journal={IEEE Transactions on Image Processing},
  year={2017},
  volume={26},
  pages={5298-5311}
}
  • Wei Shen, Kai Zhao, A. Yuille
  • Published 13 September 2016
  • Computer Science, Environmental Science
  • IEEE Transactions on Image Processing
Object skeletons are useful for object representation and object detection. They are complementary to the object contour, and provide extra information, such as how object scale (thickness) varies among object parts. But object skeleton extraction from natural images is very challenging, because it requires the extractor to be able to capture both local and non-local image context in order to determine the scale of each skeleton pixel. In this paper, we present a novel fully convolutional… 
DeepFlux for Skeletons in the Wild
TLDR
This article training a CNN to predict a two-dimensional vector field, which maps each scene point to a candidate skeleton pixel, in the spirit of flux-based skeletonization algorithms, achieves consistently superior performance over state-of-the-art methods.
DeepFlux for Skeleton Detection in the Wild
TLDR
This article follows the spirit of flux-based algorithms for medial axis recovery by training a convolutional neural network to predict a two-dimensional vector field encoding the flux representation, which captures the position of skeletal pixels relative to semantically meaningful entities resulting in precise skeleton detection.
U-Net Based Convolutional Neural Network for Skeleton Extraction
  • Oleg Panichev, A. Voloshyna
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2019
TLDR
U-net based approach for direct skeleton extraction of the object within Pixel SkelNetOn - CVPR 2019 challenge is introduced, inspired by CNNs success in skeleton extraction from real images task.
Genetic Feature Fusion for Object Skeleton Detection
TLDR
A genetic NAS method to automatically search on a newly designed architecture search space for adaptive multiscale feature fusion and introduces a symmetric encoder-decoder search space based on reversing the VGG network, in which the decoder can reuse the ImageNet pretrained model of VGG.
MSB-FCN: Multi-Scale Bidirectional FCN for Object Skeleton Extraction
TLDR
This work proposes a novel network architecture, the Multi-Scale Bidirectional Fully Convolutional Network (MSB-FCN), to better gather and enhance multi-scale high-level contextual information and achieves significant improvements over the state-of-the-art algorithms.
An Improved Skeleton Extraction Method via Multi-Task and Variable Coefficient Loss Function in Natural Images
TLDR
The experimental results verify that both the skeleton accuracy and the generalization abilities are promoted benefiting from the regression task and the new loss function in the new method, as satisfactory results are achieved on three public datasets, i.e., SK-LARGE, SK-SMALL, and WH-SYMMAX.
Hi-Fi: Hierarchical Feature Integration for Skeleton Detection
TLDR
A new convolutional neural network architecture is presented by introducing a novel hierarchical feature integration mechanism, named Hi-Fi, to address the object skeleton detection problem and significantly outperforms the state-of-the-art methods in terms of effectively fusing features from very different scales.
U-Net based skeletonization and bag of tricks
  • N. Nguyen
  • Computer Science
    2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
  • 2021
TLDR
This paper proposes the solution for the Pixel SkelNetOn challenge in the third edition of the "Deep Learning for Geometric Computing" workshop at ICCV 2021, which includes modification of U-Net architecture using the attention mechanism, implementation of auxiliary task learning for a more effective training process and application of several tricks for improving the skeletonization model’s performance.
ProMask: Probability Mask for Skeleton Detection
TLDR
The proposed ProMask is a novel skeleton detection model that includes the probability mask and vector router, which explicitly encodes skeletons with segmentation signals, which can provide more supervised information to learn and pay more attention to ground-truth skeleton pixels.
Fusing Image and Segmentation Cues for Skeleton Extraction in the Wild
TLDR
A two-stream fully convolutional neural network which uses the original image and its corresponding semantic segmentation probability map as inputs and predicts the skeleton map using merged multi-scale features is proposed.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 53 REFERENCES
Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs
TLDR
A fully convolutional network with multiple scale-associated side outputs is presented to address object skeleton extraction in natural images, and achieves promising results on two skeleton extraction datasets, and significantly outperforms other competitors.
DeepContour: A deep convolutional feature learned by positive-sharing loss for contour detection
TLDR
This work shows that contour detection accuracy can be improved by instead making the use of the deep features learned from convolutional neural networks (CNNs), while rather than using the networks as a blackbox feature extractor, it customize the training strategy by partitioning contour (positive) data into subclasses and fitting each subclass by different model parameters.
Very Deep Convolutional Networks for Large-Scale Image Recognition
TLDR
This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Fully Convolutional Networks for Semantic Segmentation
TLDR
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Deeply-Supervised Nets
TLDR
The proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent, and extends techniques from stochastic gradient methods to analyze the algorithm.
Active skeleton for non-rigid object detection
TLDR
This paper uses the skeleton (medial axis) information to capture the main structure of an object, which has the particular advantage in modeling articulation and non-rigid deformation and applies sum-and-max algorithm to perform rapid object detection.
What is an object?
TLDR
A generic objectness measure, quantifying how likely it is for an image window to contain an object of any class, is presented, combining in a Bayesian framework several image cues measuring characteristics of objects, such as appearing different from their surroundings and having a closed boundary.
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: A method for focus-of-attention
  • T. Lindeberg
  • Computer Science
    International Journal of Computer Vision
  • 2005
TLDR
A multiscale representation of grey-level shape called the scale-space primal sketch is presented, which gives a qualitative description of image structure, which allows for detection of stable scales and associated regions of interest in a solely bottom-up data-driven way.
Learning-Based Symmetry Detection in Natural Images
TLDR
This work creates and makes publicly available a ground-truth dataset for symmetry detection in natural images, and uses supervised learning to learn how to combine these cues, and employs MIL to accommodate the unknown scale and orientation of the symmetric structures.
ImageNet Large Scale Visual Recognition Challenge
TLDR
The creation of this benchmark dataset and the advances in object recognition that have been possible as a result are described, and the state-of-the-art computer vision accuracy with human accuracy is compared.
...
1
2
3
4
5
...