Annotation-Free and One-Shot Learning for Instance Segmentation of Homogeneous Object Clusters.
Zheng WuRuiheng ChangJiaxu MaCewu LuChi-Keung TangPublished in: IJCAI (2018)
Keyphrases
- object segmentation
- multiple objects
- image segments
- data objects
- segmentation method
- image segmentation
- clustering algorithm
- d objects
- bounding box
- segmentation algorithm
- signed distance
- similar objects
- level set
- object model
- multiscale
- region growing
- background pixels
- edge detection
- unsupervised clustering
- object contours
- hierarchical clustering
- metadata
- fully unsupervised
- cluster analysis
- global shape
- active learning
- energy function
- individual objects
- graph cut segmentation
- final segmentation
- object shape
- foreground and background
- shape prior
- image annotation
- background subtraction
- image regions
- moving objects
- object categories
- semantic annotation
- object tracking
- graph cuts
- medical images
- object regions
- weakly labeled
- data points