A Three-Stage Self-Training Framework for Semi-Supervised Semantic Segmentation
This work provides an incremental improvement in semi-supervised semantic segmentation for researchers and practitioners by reducing the reliance on expensive pixel-level annotations.
This paper addresses the high cost of pixel-level annotations for semantic segmentation by proposing a three-stage self-training framework. The method extracts statistical information from pseudo-masks to reduce prediction uncertainty and enforce segmentation consistency, achieving state-of-the-art performance in semi-supervised semantic segmentation.
Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high quality segmentation masks. To obtain such annotations is highly expensive and time consuming, in particular, in semantic segmentation where pixel-level annotations are required. In this work, we address this problem by proposing a holistic solution framed as a three-stage self-training framework for semi-supervised semantic segmentation. The key idea of our technique is the extraction of the pseudo-masks statistical information to decrease uncertainty in the predicted probability whilst enforcing segmentation consistency in a multi-task fashion. We achieve this through a three-stage solution. Firstly, we train a segmentation network to produce rough pseudo-masks which predicted probability is highly uncertain. Secondly, we then decrease the uncertainty of the pseudo-masks using a multi-task model that enforces consistency whilst exploiting the rich statistical information of the data. We compare our approach with existing methods for semi-supervised semantic segmentation and demonstrate its state-of-the-art performance with extensive experiments.