← Back to all news
arXiv Machine Learning By Sebastian Doerrich, Francesco Di Salvo, Shyam Nandan Rai, Marco Lents, Christian Ledig

Simple, Safe, and Overlooked: Reclaiming Sustainable Domain Generalization with Statistical Color Matching

Read the original on arXiv Machine Learning →

The paper introduces Colorist, a data‑augmentation method that uses classical statistical color matching to generate domain‑shifted medical images. By applying global mean‑standard‑deviation matching in RGB space, Colorist creates structurally intact variations without neural networks, outperforming deep generative models in fidelity and color alignment. Across multiple medical imaging datasets, it boosts balanced accuracy by up to 9% over state‑of‑the‑art domain‑generalization regularizers and 13% over no augmentation, while reducing computational cost and preserving anatomical structure.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 2

StainPresetNet: Stain Preset Network for Fast Multi-to-Multi Stain Normalization

StainPresetNet is a new framework for stain normalization that combines structural preservation with dataset-level color mapping while remaining computationally efficient. It uses pixel-wise normalization guided by preset reference images, allowing multi-directional adaptability without retraining. Experiments on cytopathology and histopathology datasets show that it outperforms conventional methods in color mapping accuracy, improves classifier generalization, and cuts computational overhead by 90% compared to existing deep learning approaches.

By Hongtao Kang, Die Luo, Li Chen, Jing Cai, Junbo Hu, Xiuli Liu, Shenghua Cheng
More like this →
Hugging Face Trending Papers
Jul 27

Color Fundus Photography Analysis: Co-evolution of Data, Preprocessing, and Modeling toward Multimodal AI

Color Fundus Photography (CFP) is a primary non-invasive imaging modality for large-scale screening of ophthalmic and systemic diseases. Existing surveys mainly summarize task-specific algorithms, datasets, or preprocessing techniques independently, lacking a unified perspective on their co-evolution with modern artificial intelligence.

multimodal
More like this →
arXiv AI
Sep 3

InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation

InstEditSeg is a generative framework that treats medical segmentation as an instruction-driven image editing task. Instead of producing binary masks, it renders a color-coded overlay on the original image guided by textual instructions, leveraging latent diffusion models to align with natural image distributions and reduce domain gaps. The method incorporates a DINOv3 visual encoder and a multi-scale feature pyramid fused into the diffusion U‑Net, and uses a dual‑branch classifier‑free guidance strategy to lower inference cost, achieving competitive accuracy on polyp and skin lesion datasets while improving cross‑domain generalization and multi‑lesion segmentation.

By Ziquan Liu, Zhewei Zhu, Xuyang Shi
diffusioncomputer-visionbenchmarks
More like this →
arXiv AI
1d ago

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Paint-Anything introduces a unified hex-prompt interface that allows users to specify any 24‑bit hex color for both image generation and editing. The method trains on a new Paint‑500K dataset created from real images with object grounding, perceptual color labeling, and editing‑pair synthesis, and supplements this with pure‑color anchors to address shadow‑induced color inaccuracies. Evaluated on the newly proposed Any Color Benchmark (ACBench), Paint‑Anything achieves significant improvements over the base FLUX.2‑4B model, boosting T2I and editing scores by 85.3 % and 28.3 % respectively, and outperforms competing methods on the CompColor metric.

By Ji Xie, Dewei Zhou, Xinyu Huang, Zhennan Chen, Xun Wang
llmsdiffusionbenchmarksdata-engineering
More like this →