Small Sample Learning of Superpixel Classifiers for EM Segmentation- Extended Version
This addresses the tedious and costly annotation bottleneck in EM segmentation for researchers and practitioners, though it is incremental as it builds on existing interactive and semi-supervised methods.
The paper tackles the problem of training superpixel classifiers for EM segmentation by proposing an active semi-supervised learning scheme that reduces annotation effort, achieving classifier accuracy almost as high as using complete groundtruth with less than 20% of data points.
Pixel and superpixel classifiers have become essential tools for EM segmentation algorithms. Training these classifiers remains a major bottleneck primarily due to the requirement of completely annotating the dataset which is tedious, error-prone and costly. In this paper, we propose an interactive learning scheme for the superpixel classifier for EM segmentation. Our algorithm is "active semi-supervised" because it requests the labels of a small number of examples from user and applies label propagation technique to generate these queries. Using only a small set ($<20\%$) of all datapoints, the proposed algorithm consistently generates a classifier almost as accurate as that estimated from a complete groundtruth. We provide segmentation results on multiple datasets to show the strength of these classifiers.