PLESS: Pseudo-Label Enhancement with Spreading Scribbles for Weakly Supervised Segmentation

2026-02-12

AI Summary

This work addresses the challenges of low-quality pseudo-labels, sparse supervision signals, and noise inherent in scribble-supervised segmentation. To this end, the authors propose a general pseudo-label enhancement strategy that propagates scribble annotations within semantically coherent regions defined by hierarchical image partitioning, thereby leveraging spatial coherence to improve the consistency and reliability of pseudo-labels. The proposed mechanism is model-agnostic and can be seamlessly integrated into existing scribble-supervised segmentation frameworks. Extensive experiments on two cardiac MRI datasets—ACDC and MSCMRseg—demonstrate consistent performance gains across four state-of-the-art methods, validating the effectiveness and broad applicability of the approach.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Reasoning under Uncertainty: Graphical Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Privacy-enhancing technologies

Abstract

Weakly supervised learning with scribble annotations uses sparse user-drawn strokes to indicate segmentation labels on a small subset of pixels. This annotation reduces the cost of dense pixel-wise labeling, but suffers inherently from noisy and incomplete supervision. Recent scribble-based approaches in medical image segmentation address this limitation using pseudo-label-based training; however, the quality of the pseudo-labels remains a key performance limit. We propose PLESS, a generic pseudo-label enhancement strategy which improves reliability and spatial consistency. It builds on a hierarchical partitioning of the image into a hierarchy of spatially coherent regions. PLESS propagates scribble information to refine pseudo-labels within semantically coherent regions. The framework is model-agnostic and easily integrates into existing pseudo-label methods. Experiments on two public cardiac MRI datasets (ACDC and MSCMRseg) across four scribble-supervised algorithms show consistent improvements in segmentation accuracy. Code will be made available on GitHub upon acceptance.

Problem

• weakly supervised segmentation
• scribble annotation
• pseudo-label
• noisy supervision
• incomplete supervision

Innovation

• pseudo-label enhancement
• scribble supervision
• hierarchical partitioning
• weakly supervised segmentation
• spatial consistency