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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ghamsarian, Negin, Nasirihaghighi, Sahar, Schoeffmann, Klaus, Sznitman, Raphael
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910938729283584
author Ghamsarian, Negin
Nasirihaghighi, Sahar
Schoeffmann, Klaus
Sznitman, Raphael
author_facet Ghamsarian, Negin
Nasirihaghighi, Sahar
Schoeffmann, Klaus
Sznitman, Raphael
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07691
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation
Ghamsarian, Negin
Nasirihaghighi, Sahar
Schoeffmann, Klaus
Sznitman, Raphael
Computer Vision and Pattern Recognition
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.
title Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.07691