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

arXiv: https://arxiv.org/abs/2601.18619 · HTML: https://mlsanity.com/paper/2601.18619/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [VICRegL: Self-Supervised Learning of Local Visual Features](https://mlsanity.com/paper/2210.01571/) (2022)
- [CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding](https://mlsanity.com/paper/2304.09670/) (2023)
- [A Machine Learning Benchmark for Facies Classification](https://mlsanity.com/paper/1901.07659/) (2019)
- [MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction](https://mlsanity.com/paper/2301.00345/) (2023)
- [Self-Supervised Alignment Learning for Medical Image Segmentation](https://mlsanity.com/paper/2406.15699/) (2024)
- [Benchmarking Human and Automated Prompting in the Segment Anything Model](https://mlsanity.com/paper/2410.22048/) (2024)
- [Self-supervised Semantic Segmentation: Consistency over Transformation](https://mlsanity.com/paper/2309.00143/) (2023)
- [A Large-scale Benchmark on Geological Fault Delineation Models: Domain Shift, Training Dynamics, Generalizability, Evaluation and Inferential Behavior](https://mlsanity.com/paper/2505.08585/) (2025)
- [Self-Supervised Learning for Image Segmentation: A Comprehensive Survey](https://mlsanity.com/paper/2505.13584/) (2025)
- [CRACKS: Crowdsourcing Resources for Analysis and Categorization of Key Subsurface faults](https://mlsanity.com/paper/2408.11185/) (2024)

## Abstract (arXiv)

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.