Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation

TL;DR

This paper introduces CPCL, a semi-supervised semantic segmentation method using two collaborative networks that balance high-quality pseudo labels and exploration, achieving state-of-the-art results.

Contribution

The novel CPCL approach employs dual networks with intersection and union supervision to balance reliability and exploration in semi-supervised learning.

Findings

Achieves state-of-the-art semi-supervised segmentation performance

Effectively balances high-quality pseudo labels with exploration

Reduces impact of suspicious pseudo labels through dynamic re-weighting

Abstract

Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels. Addressing that, we propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel, and the pseudo supervision is implemented based on both the agreement and disagreement of the two predictions. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision, while the other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity. Thus, the collaboration of conservative evolution and progressive exploration can be achieved. To reduce the influences of the suspicious pseudo labels, the loss is dynamic re-weighted according to the prediction confidence. Extensive experiments demonstrate that CPCL achieves state-of-the-art performance for semi-supervised semantic segmentation.