Side-output Residual Network for Object Symmetry Detection in the Wild
SRN is build on Holistically-Nested Edge Detection (HED) [1] with Residual Unit (RU). RU is used to compute the residual between output image and side-output of SRN.
- Install prerequisites for Caffe (http://caffe.berkeleyvision.org/installation.html#prequequisites)
- Build HED (https://github.com/s9xie/hed)
- Copy folder
SRN
to 'example/' in HED.
- Download benchmark Sym-PASCAL trainning set Our dataset Sym-PASCAL derived from PASCAL 2011 segmentation dataset [1]. Download:(OneDrive) or (BaiduYun)
- Download the Pre-trained VGG [3] model. (VGG19) Copy it to 'example/SRN/'
- Change the dataset directory of 'train_val.prototxt'
- Change the directory of
solver.prototxt
- Run
solve.py
- Change the dataset directory of 'SRNtest.py'
- run 'SRNtest.py'
We use the evaluation code of [3] to draw the PR curve. The code can be download (spb-mil)
(Pre-trained SRN model on Sym-PASCAL)
(WH-SYMMAX) mostly taken from http://wei-shen.weebly.com/publications.html
(SK506) mostly taken from http://wei-shen.weebly.com/publications.html
Ref
[1] S. Xie and Z. Tu. Holistically-nested edge detection. In International Conference on Computer Vision, 2015
[2] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2011 (VOC2011) Results. http://www.pascal-network.org/challenges/VOC/voc2011/workshop/index.html.
[3] S. Tsogkas and I. Kokkinos. Learning-based symmetry detection in natural images. In European Conference on Computer Vision