Scale-Aware Self-Supervised Learning for Segmentation of Small and Sparse Structures
This addresses segmentation challenges in scientific imaging domains like seismic and neuroimaging, offering a general principle for SSL design, though it appears incremental as an adaptation of existing SSL pipelines.
The paper tackles the problem of self-supervised learning (SSL) for segmentation of small and sparse structures, which existing methods struggle with, and shows that their scale-aware SSL adaptation improves accuracy by up to 13% for fault segmentation and 5% for cell delineation.
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.