Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation

TL;DR

This paper introduces ENCORE, a dynamic, feedback-driven thresholding method for pseudo-label selection in semi-supervised semantic segmentation, eliminating the need for manual threshold tuning and improving performance in data-scarce scenarios.

Contribution

ENCORE is a novel adaptive thresholding strategy that estimates class-wise true-positive confidence and adjusts pseudo-label filtering dynamically during training.

Findings

ENCORE improves segmentation accuracy across multiple datasets.

It outperforms static thresholding methods in low-data conditions.

The method seamlessly integrates with existing frameworks.

Abstract

Semi-supervised learning leverages unlabeled data to enhance model performance, addressing the limitations of fully supervised approaches. Among its strategies, pseudo-supervision has proven highly effective, typically relying on one or multiple teacher networks to refine pseudo-labels before training a student network. A common practice in pseudo-supervision is filtering pseudo-labels based on pre-defined confidence thresholds or entropy. However, selecting optimal thresholds requires large labeled datasets, which are often scarce in real-world semi-supervised scenarios. To overcome this challenge, we propose Ensemble-of-Confidence Reinforcement (ENCORE), a dynamic feedback-driven thresholding strategy for pseudo-label selection. Instead of relying on static confidence thresholds, ENCORE estimates class-wise true-positive confidence within the unlabeled dataset and continuously adjusts thresholds based on the model's response to different levels of pseudo-label filtering. This feedback-driven mechanism ensures the retention of informative pseudo-labels while filtering unreliable ones, enhancing model training without manual threshold tuning. Our method seamlessly integrates into existing pseudo-supervision frameworks and significantly improves segmentation performance, particularly in data-scarce conditions. Extensive experiments demonstrate that integrating ENCORE with existing pseudo-supervision frameworks enhances performance across multiple datasets and network architectures, validating its effectiveness in semi-supervised learning.