# DINO-MX: A Modular & Flexible Framework for Self-Supervised Learning

arXiv: https://arxiv.org/abs/2511.01610 · HTML: https://mlsanity.com/paper/2511.01610/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 39 references that are in the map.
- First posted on arXiv 3 Nov 2025.

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

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography](https://mlsanity.com/paper/2403.17834/) (2024)
- [Explainable artificial intelligence (XAI) in deep learning-based medical image analysis](https://mlsanity.com/paper/2107.10912/) (2021)
- [On the Challenges and Perspectives of Foundation Models for Medical Image Analysis](https://mlsanity.com/paper/2306.05705/) (2023)
- [k-Nearest Neighbour Classifiers: 2nd Edition (with Python examples)](https://mlsanity.com/paper/2004.04523/) (2020)
- [Are Natural Domain Foundation Models Useful for Medical Image Classification?](https://mlsanity.com/paper/2310.19522/) (2023)
- [Robustness Analysis on Foundational Segmentation Models](https://mlsanity.com/paper/2306.09278/) (2023)
- [Open Challenges and Opportunities in Federated Foundation Models Towards Biomedical Healthcare](https://mlsanity.com/paper/2405.06784/) (2024)
- [A Simple Recipe for Competitive Low-compute Self supervised Vision Models](https://mlsanity.com/paper/2301.09451/) (2023)
- [Class-Discriminative Attention Maps for Vision Transformers](https://mlsanity.com/paper/2312.02364/) (2023)
- [Adaptive Layer Selection for Efficient Vision Transformer Fine-Tuning](https://mlsanity.com/paper/2408.08670/) (2024)
- [Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective](https://mlsanity.com/paper/2410.22217/) (2024)
- [Institutional Platform for Secure Self-Service Large Language Model Exploration](https://mlsanity.com/paper/2402.00913/) (2024)

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

- [Vision Foundry: A System for Training Foundational Vision AI Models](https://mlsanity.com/paper/2512.11837/) (2025)
- [DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT](https://mlsanity.com/paper/2606.07775/) (2026)

## Abstract (arXiv)

Vision Foundation Models (VFMs) have advanced representation learning through self-supervised methods. However, existing training pipelines are often inflexible, domain-specific, or computationally expensive, which limits their usability across different domains and resource settings. DINO-MX is a modular and extensible training framework that combines the core principles of DINO, DINOv2 and DINOv3 within a unified configuration-driven system. It supports a variety of transformer-based architectures and is fully compatible with the Hugging Face ecosystem. The framework includes multiple training strategies such as low-rank adaptation (LoRA), layer freezing, and knowledge distillation, along with support for distributed training through both Distributed Data Parallel (DDP) and Fully Sharded Data Parallel (FSDP). DINO-MX is designed to work with both natural and specialized data types, including single- and multi-channel images. Experimental results on diverse datasets show that DINO-MX achieves competitive performance while significantly reducing computational costs. Additionally, it offers interpretability tools and a label-guided data augmentation method that improves attention-based localization without the need for extra detection or segmentation heads. DINO-MX provides a reproducible and scalable foundation for developing, adapting, and benchmarking self-supervised vision models across a range of research and real-world applications.