# Seeing the Whole in the Parts in Self-Supervised Representation Learning

arXiv: https://arxiv.org/abs/2501.02860 · HTML: https://mlsanity.com/paper/2501.02860/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2025.

## Built on by (most cited first, 2 of 2)

- [Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning](https://mlsanity.com/paper/2510.22322/) (2025)
- [Self-Supervised Learning with a Multi-Task Latent Space Objective](https://mlsanity.com/paper/2602.05845/) (2026)

## Abstract (arXiv)

Recent successes in self-supervised learning (SSL) model spatial co-occurrences of visual features either by masking portions of an image or by aggressively cropping it. Here, we propose a new way to model spatial co-occurrences by aligning local representations (before pooling) with a global image representation. We present CO-SSL, a family of instance discrimination methods and show that it outperforms previous methods on several datasets, including ImageNet-1K where it achieves 71.5% of Top-1 accuracy with 100 pre-training epochs. CO-SSL is also more robust to noise corruption, internal corruption, small adversarial attacks, and large training crop sizes. Our analysis further indicates that CO-SSL learns highly redundant local representations, which offers an explanation for its robustness. Overall, our work suggests that aligning local and global representations may be a powerful principle of unsupervised category learning.