Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structures

2026-01-26

AI Summary

This work addresses the significant performance degradation of self-supervised learning in segmenting small-scale, sparse, or irregularly shaped structures—a limitation arising from pretraining strategies predominantly designed for large, homogeneous regions and thus ill-suited for fine-grained scientific imaging targets. To bridge this gap, the study introduces, for the first time, a scale-aware mechanism into self-supervised learning by proposing a small-window cropping augmentation strategy during pretraining. This approach explicitly aligns the model’s receptive focus with the target structures’ scale and sparsity characteristics. Evaluated on seismic fault segmentation and neuronal cell structure delineation tasks, the method achieves accuracy improvements of 13% and 5%, respectively, substantially outperforming existing baselines while preserving performance on large-scale structures. The framework establishes a general design principle for fine-structure segmentation in scientific imaging.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Structured Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Self-supervised learning (SSL) has emerged as a powerful strategy for representation learning under limited annotation regimes, yet its effectiveness remains highly sensitive to many factors, especially the nature of the target task. In segmentation, existing pipelines are typically tuned to large, homogeneous regions, but their performance drops when objects are small, sparse, or locally irregular. In this work, we propose a scale-aware SSL adaptation that integrates small-window cropping into the augmentation pipeline, zooming in on fine-scale structures during pretraining. We evaluate this approach across two domains with markedly different data modalities: seismic imaging, where the goal is to segment sparse faults, and neuroimaging, where the task is to delineate small cellular structures. In both settings, our method yields consistent improvements over standard and state-of-the-art baselines under label constraints, improving accuracy by up to 13% for fault segmentation and 5% for cell delineation. In contrast, large-scale features such as seismic facies or tissue regions see little benefit, underscoring that the value of SSL depends critically on the scale of the target objects. Our findings highlight the need to align SSL design with object size and sparsity, offering a general principle for buil ding more effective representation learning pipelines across scientific imaging domains.

Problem

• self-supervised learning
• small structures
• sparse segmentation
• scale-aware
• scientific imaging

Innovation

• scale-aware
• self-supervised learning
• small and sparse structures
• segmentation
• scientific imaging