# Bridging the gap between Natural and Medical Images through Deep Colorization

arXiv: https://arxiv.org/abs/2005.10589 · HTML: https://mlsanity.com/paper/2005.10589/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2020.

## Built on by (most cited first, 11 of 11)

- [The Intrinsic Manifolds of Radiological Images and their Role in Deep Learning](https://mlsanity.com/paper/2207.02797/) (2022)
- [Dataset Distillation in Medical Imaging: A Feasibility Study](https://mlsanity.com/paper/2407.14429/) (2024)
- [ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimization](https://mlsanity.com/paper/2404.18831/) (2024)
- [CB-HVTNet: A channel-boosted hybrid vision transformer network for lymphocyte assessment in histopathological images](https://mlsanity.com/paper/2305.09211/) (2023)
- [Adversarial-Robust Transfer Learning for Medical Imaging via Domain Assimilation](https://mlsanity.com/paper/2402.16005/) (2024)
- [Multi-Sample zeta-mixup: Richer, More Realistic Synthetic Samples from a p-Series Interpolant](https://mlsanity.com/paper/2204.03323/) (2022)
- [Minimal High-Resolution Patches Are Sufficient for Whole Slide Image Representation via Cascaded Dual-Scale Reconstruction](https://mlsanity.com/paper/2508.01641/) (2025)
- [Medical Visual Prompting (MVP): A Unified Framework for Versatile and High-Quality Medical Image Segmentation](https://mlsanity.com/paper/2404.01127/) (2024)
- [Out-of-distribution data supervision towards biomedical semantic segmentation](https://mlsanity.com/paper/2507.12105/) (2025)
- [Visualizing the Invisible: Enhancing Radiologist Performance in Breast Mammography via Task-Driven Chromatic Encoding](https://mlsanity.com/paper/2602.07568/) (2026)
- [Multi-Level Analyzation of Imbalance to Resolve Non-IID-Ness in Federated Learning](https://mlsanity.com/paper/2606.10250/) (2026)

## Abstract (arXiv)

Deep learning has thrived by training on large-scale datasets. However, in many applications, as for medical image diagnosis, getting massive amount of data is still prohibitive due to privacy, lack of acquisition homogeneity and annotation cost. In this scenario, transfer learning from natural image collections is a standard practice that attempts to tackle shape, texture and color discrepancies all at once through pretrained model fine-tuning. In this work, we propose to disentangle those challenges and design a dedicated network module that focuses on color adaptation. We combine learning from scratch of the color module with transfer learning of different classification backbones, obtaining an end-to-end, easy-to-train architecture for diagnostic image recognition on X-ray images. Extensive experiments showed how our approach is particularly efficient in case of data scarcity and provides a new path for further transferring the learned color information across multiple medical datasets.