# S5CL: Unifying Fully-Supervised, Self-Supervised, and Semi-Supervised Learning Through Hierarchical Contrastive Learning

arXiv: https://arxiv.org/abs/2203.07307 · HTML: https://mlsanity.com/paper/2203.07307/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 25 references that are in the map.
- First posted on arXiv 14 Mar 2022.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [S4L: Self-Supervised Semi-Supervised Learning](https://mlsanity.com/paper/1905.03670/) (2019)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [A Metric Learning Reality Check](https://mlsanity.com/paper/2003.08505/) (2020)
- [CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2102.09559/) (2021)
- [Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases](https://mlsanity.com/paper/2007.13916/) (2020)
- [Self-Path: Self-supervision for Classification of Pathology Images with Limited Annotations](https://mlsanity.com/paper/2008.05571/) (2020)
- [Semi-Supervised Learning using Siamese Networks](https://mlsanity.com/paper/2109.00794/) (2021)

## Built on by (most cited first, 7 of 7)

- [Domain Generalization in Computational Pathology: Survey and Guidelines](https://mlsanity.com/paper/2310.19656/) (2023)
- [Vim4Path: Self-Supervised Vision Mamba for Histopathology Images](https://mlsanity.com/paper/2404.13222/) (2024)
- [Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey](https://mlsanity.com/paper/2403.01909/) (2024)
- [From Barlow Twins to Triplet Training: Differentiating Dementia with Limited Data](https://mlsanity.com/paper/2404.06253/) (2024)
- [Dense Self-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/2407.20395/) (2024)
- [Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks](https://mlsanity.com/paper/2404.14941/) (2024)
- [Pix2Rep-v2: Data-Efficient Representation Learning for Dense Medical Imaging Applications](https://mlsanity.com/paper/2609.01427/) (2026)

## Abstract (arXiv)

In computational pathology, we often face a scarcity of annotations and a large amount of unlabeled data. One method for dealing with this is semi-supervised learning which is commonly split into a self-supervised pretext task and a subsequent model fine-tuning. Here, we compress this two-stage training into one by introducing S5CL, a unified framework for fully-supervised, self-supervised, and semi-supervised learning. With three contrastive losses defined for labeled, unlabeled, and pseudo-labeled images, S5CL can learn feature representations that reflect the hierarchy of distance relationships: similar images and augmentations are embedded the closest, followed by different looking images of the same class, while images from separate classes have the largest distance. Moreover, S5CL allows us to flexibly combine these losses to adapt to different scenarios. Evaluations of our framework on two public histopathological datasets show strong improvements in the case of sparse labels: for a H&E-stained colorectal cancer dataset, the accuracy increases by up to 9% compared to supervised cross-entropy loss; for a highly imbalanced dataset of single white blood cells from leukemia patient blood smears, the F1-score increases by up to 6%.