# Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision

arXiv: https://arxiv.org/abs/2404.15672 · HTML: https://mlsanity.com/paper/2404.15672/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 105 references that are in the map.
- First posted on arXiv 24 Apr 2024.

## Builds on (most cited first, 30 of 74)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [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)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Prototypical Contrastive Learning of Unsupervised Representations](https://mlsanity.com/paper/2005.04966/) (2020)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [Contrastive learning of global and local features for medical image segmentation with limited annotations](https://mlsanity.com/paper/2006.10511/) (2020)
- [Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/2011.10043/) (2020)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images](https://mlsanity.com/paper/2003.09871/) (2020)

## Built on by (most cited first, 13 of 13)

- [CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning](https://mlsanity.com/paper/2504.13820/) (2025)
- [AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images](https://mlsanity.com/paper/2504.10972/) (2025)
- [Impact of Clinical Image Quality on Efficient Foundation Model Finetuning](https://mlsanity.com/paper/2508.11864/) (2025)
- [M3Ret: Unleashing Zero-shot Multimodal Medical Image Retrieval via Self-Supervision](https://mlsanity.com/paper/2509.01360/) (2025)
- [FedPartWhole: Federated domain generalization via consistent part-whole hierarchies](https://mlsanity.com/paper/2407.14792/) (2024)
- [ACE: Anatomically Consistent Embeddings in Composition and Decomposition](https://mlsanity.com/paper/2501.10131/) (2025)
- [A Flag Decomposition for Hierarchical Datasets](https://mlsanity.com/paper/2502.07782/) (2025)
- [DiSSECT: Structuring Transfer-Ready Medical Image Representations through Discrete Self-Supervision](https://mlsanity.com/paper/2509.18765/) (2025)
- [Lamps: Learning Anatomy from Multiple Perspectives via Self-supervision in Chest Radiographs](https://mlsanity.com/paper/2512.22872/) (2025)
- [M-IDoL: Information Decomposition for Modality-Specific and Diverse Representation Learning in Medical Foundation Model](https://mlsanity.com/paper/2604.08936/) (2026)
- [Beyond Masks: The Case for Medical Image Parsing](https://mlsanity.com/paper/2605.11438/) (2026)
- [OrganLens: Organ-Specific Representation Learning for CT Foundation Models](https://mlsanity.com/paper/2607.25164/) (2026)
- [Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning](https://mlsanity.com/paper/2610.13915/) (2026)

## Abstract (arXiv)

Humans effortlessly interpret images by parsing them into part-whole hierarchies; deep learning excels in learning multi-level feature spaces, but they often lack explicit coding of part-whole relations, a prominent property of medical imaging. To overcome this limitation, we introduce Adam-v2, a new self-supervised learning framework extending Adam [79] by explicitly incorporating part-whole hierarchies into its learning objectives through three key branches: (1) Localizability, acquiring discriminative representations to distinguish different anatomical patterns; (2) Composability, learning each anatomical structure in a parts-to-whole manner; and (3) Decomposability, comprehending each anatomical structure in a whole-to-parts manner. Experimental results across 10 tasks, compared to 11 baselines in zero-shot, few-shot transfer, and full fine-tuning settings, showcase Adam-v2's superior performance over large-scale medical models and existing SSL methods across diverse downstream tasks. The higher generality and robustness of Adam-v2's representations originate from its explicit construction of hierarchies for distinct anatomical structures from unlabeled medical images. Adam-v2 preserves a semantic balance of anatomical diversity and harmony in its embedding, yielding representations that are both generic and semantically meaningful, yet overlooked in existing SSL methods. All code and pretrained models are available at https://github.com/JLiangLab/Eden.