We consider the task of semi-supervised semantic segmentation, where we aim to produce pixel-wise semantic object masks given only a small number of human-labeled training examples. We focus on iterative self-training methods in which we explore the behavior of self-training over multiple refinement stages. We show that iterative self-training leads to performance degradation if done na\"ively with a fixed ratio of human-labeled to pseudo-labeled training examples. We propose Greedy Iterative Self-Training (GIST) and Random Iterative Self-Training (RIST) strategies that alternate between training on either human-labeled data or pseudo-labeled data at each refinement stage, resulting in a performance boost rather than degradation. We further show that GIST and RIST can be combined with existing semi-supervised learning methods to boost performance.
@article{arxiv.2103.17105,
title = {The GIST and RIST of Iterative Self-Training for Semi-Supervised Segmentation},
author = {Eu Wern Teh and Terrance DeVries and Brendan Duke and Ruowei Jiang and Parham Aarabi and Graham W. Taylor},
journal= {arXiv preprint arXiv:2103.17105},
year = {2022}
}
Comments
To appear in the Conference on Computer and Robot Vision (CRV), 2022