# Consistent View Alignment Improves Foundation Models for 3D Medical Image Segmentation

arXiv: https://arxiv.org/abs/2509.13846 · HTML: https://mlsanity.com/paper/2509.13846/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 26 of 26)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [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)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Understanding Dimensional Collapse in Contrastive Self-supervised Learning](https://mlsanity.com/paper/2110.09348/) (2021)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [Learning from Noisy Labels with Distillation](https://mlsanity.com/paper/1703.02391/) (2017)
- [Contrastive Masked Autoencoders are Stronger Vision Learners](https://mlsanity.com/paper/2207.13532/) (2022)
- [Intriguing Properties of Contrastive Losses](https://mlsanity.com/paper/2011.02803/) (2020)
- [VoCo: A Simple-yet-Effective Volume Contrastive Learning Framework for 3D Medical Image Analysis](https://mlsanity.com/paper/2402.17300/) (2024)
- [Wasserstein Dependency Measure for Representation Learning](https://mlsanity.com/paper/1903.11780/) (2019)
- [Making Risk Minimization Tolerant to Label Noise](https://mlsanity.com/paper/1403.3610/) (2014)
- [Robust Contrastive Learning against Noisy Views](https://mlsanity.com/paper/2201.04309/) (2022)
- [Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video](https://mlsanity.com/paper/2310.08584/) (2023)
- [MIS-FM: 3D Medical Image Segmentation using Foundation Models Pretrained on a Large-Scale Unannotated Dataset](https://mlsanity.com/paper/2306.16925/) (2023)
- [An OpenMind for 3D medical vision self-supervised learning](https://mlsanity.com/paper/2412.17041/) (2024)
- [Primus: Enforcing Attention Usage for 3D Medical Image Segmentation](https://mlsanity.com/paper/2503.01835/) (2025)

## Built on by (most cited first, 1 of 1)

- [Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge](https://mlsanity.com/paper/2604.11679/) (2026)

## Abstract (arXiv)

Many recent approaches in representation learning implicitly assume that uncorrelated views of a data point are sufficient to learn meaningful representations for various downstream tasks. In this work, we challenge this assumption and demonstrate that meaningful structure in the latent space does not emerge naturally. Instead, it must be explicitly induced. We propose a method that aligns representations from different views of the data to align complementary information without inducing false positives. Our experiments show that our proposed self-supervised learning method, Consistent View Alignment, improves performance for downstream tasks, highlighting the critical role of structured view alignment in learning effective representations. Our method achieved first and second place in the MICCAI 2025 SSL3D challenge when using a Primus vision transformer and ResEnc convolutional neural network, respectively. The code and pretrained model weights are released at https://github.com/Tenbatsu24/LatentCampus.