Learning from Future: A Novel Self-Training Framework for Semantic Segmentation

TL;DR

This paper introduces a novel self-training framework for semantic segmentation that learns from the future to improve pseudo-label quality and overall performance, addressing confirmation bias issues in semi-supervised learning.

Contribution

The authors propose a future-self-training strategy that updates the teacher with a virtual future student, enhancing pseudo-label accuracy in semi-supervised segmentation.

Findings

Improves pseudo-label quality and segmentation accuracy.

Effective in unsupervised domain adaptation and semi-supervised settings.

Outperforms existing self-training methods across various benchmarks.

Abstract

Self-training has shown great potential in semi-supervised learning. Its core idea is to use the model learned on labeled data to generate pseudo-labels for unlabeled samples, and in turn teach itself. To obtain valid supervision, active attempts typically employ a momentum teacher for pseudo-label prediction yet observe the confirmation bias issue, where the incorrect predictions may provide wrong supervision signals and get accumulated in the training process. The primary cause of such a drawback is that the prevailing self-training framework acts as guiding the current state with previous knowledge, because the teacher is updated with the past student only. To alleviate this problem, we propose a novel self-training strategy, which allows the model to learn from the future. Concretely, at each training step, we first virtually optimize the student (i.e., caching the gradients without applying them to the model weights), then update the teacher with the virtual future student, and finally ask the teacher to produce pseudo-labels for the current student as the guidance. In this way, we manage to improve the quality of pseudo-labels and thus boost the performance. We also develop two variants of our future-self-training (FST) framework through peeping at the future both deeply (FST-D) and widely (FST-W). Taking the tasks of unsupervised domain adaptive semantic segmentation and semi-supervised semantic segmentation as the instances, we experimentally demonstrate the effectiveness and superiority of our approach under a wide range of settings. Code will be made publicly available.