Reducing Domain Gap with Diffusion-Based Domain Adaptation for Cell Counting

• URL: http://arxiv.org/abs/2512.11763v1
• Date: Fri, 12 Dec 2025 18:19:41 GMT
• Title: Reducing Domain Gap with Diffusion-Based Domain Adaptation for Cell Counting
• Authors: Mohammad Dehghanmanshadi, Wallapak Tavanapong,
• Abstract summary: In this work, we adapt the Inversion-Based Style Transfer framework to generate synthetic microscopy images.<n>Our method combines latent-space Adaptive Instance Normalization with inversion in a diffusion model to transfer the style from real microscopy images to synthetic ones.<n>Models trained with our InST-synthesized images achieve up to 37% lower Mean Absolute Error (MAE) compared to models trained on hard-coded synthetic data.
• Score: 1.9766522384767224
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating realistic synthetic microscopy images is critical for training deep learning models in label-scarce environments, such as cell counting with many cells per image. However, traditional domain adaptation methods often struggle to bridge the domain gap when synthetic images lack the complex textures and visual patterns of real samples. In this work, we adapt the Inversion-Based Style Transfer (InST) framework originally designed for artistic style transfer to biomedical microscopy images. Our method combines latent-space Adaptive Instance Normalization with stochastic inversion in a diffusion model to transfer the style from real fluorescence microscopy images to synthetic ones, while weakly preserving content structure. We evaluate the effectiveness of our InST-based synthetic dataset for downstream cell counting by pre-training and fine-tuning EfficientNet-B0 models on various data sources, including real data, hard-coded synthetic data, and the public Cell200-s dataset. Models trained with our InST-synthesized images achieve up to 37\% lower Mean Absolute Error (MAE) compared to models trained on hard-coded synthetic data, and a 52\% reduction in MAE compared to models trained on Cell200-s (from 53.70 to 25.95 MAE). Notably, our approach also outperforms models trained on real data alone (25.95 vs. 27.74 MAE). Further improvements are achieved when combining InST-synthesized data with lightweight domain adaptation techniques such as DACS with CutMix. These findings demonstrate that InST-based style transfer most effectively reduces the domain gap between synthetic and real microscopy data. Our approach offers a scalable path for enhancing cell counting performance while minimizing manual labeling effort. The source code and resources are publicly available at: https://github.com/MohammadDehghan/InST-Microscopy.

Related papers

• Diffusion-Based Synthetic Brightfield Microscopy Images for Enhanced Single Cell Detection [0.0]
  We investigate the use of unconditional models to generate synthetic brightfield microscopy images.<n>A U-Net based diffusion model was trained and used to create datasets with varying ratios of synthetic and real images.<n>Experiments with YOLOv8, YOLOv9 and RT-DETR reveal that training with synthetic data can achieve improved detection accuracies.
  arXiv  Detail & Related papers  (2025-11-25T08:57:23Z)
• Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network [21.126506900168398]
  We present Cross-Well Aligned Masked Siamese Network (CWA-MSN), a novel representation learning framework.<n>CWA-MSN aligns embeddings of cells subjected to the same perturbation across different wells, enforcing semantic consistency despite batch effects.<n>In gene-gene relationship retrieval benchmark, CWA-MSN outperforms state-of-the-art publicly available self-supervised (OpenPhenom) and contrastive learning (CellCLIP) methods.
  arXiv  Detail & Related papers  (2025-09-24T08:48:29Z)
• Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data [53.040873127309766]
  We propose a token disentanglement process within the transformer architecture, enhancing feature separation and ensuring more effective learning.<n>Our method outperforms existing models on both in-dataset and cross-dataset evaluations.
  arXiv  Detail & Related papers  (2025-09-08T17:58:06Z)
• Style Transfer with Diffusion Models for Synthetic-to-Real Domain Adaptation [3.7051961231919393]
  We introduce two novel techniques for semantically consistent style transfer using diffusion models.<n>Experiments using GTA5 as source and Cityscapes/ACDC as target domains show that our approach produces higher quality images with lower FID scores and better content preservation.
  arXiv  Detail & Related papers  (2025-05-22T08:11:10Z)
• Dataset Distillation with Probabilistic Latent Features [9.318549327568695]
  A compact set of synthetic data can effectively replace the original dataset in downstream classification tasks.<n>We propose a novel approach that models the joint distribution of latent features.<n>Our method achieves state-of-the-art cross architecture performance across a range of backbone architectures.
  arXiv  Detail & Related papers  (2025-05-10T13:53:49Z)
• Merging synthetic and real embryo data for advanced AI predictions [69.07284335967019]
  We train two generative models using two datasets-one we created and made publicly available, and one existing public dataset-to generate synthetic embryo images at various cell stages.<n>These were combined with real images to train classification models for embryo cell stage prediction.<n>Our results demonstrate that incorporating synthetic images alongside real data improved classification performance, with the model achieving 97% accuracy compared to 94.5% when trained solely on real data.
  arXiv  Detail & Related papers  (2024-12-02T08:24:49Z)
• Generative AI-based Pipeline Architecture for Increasing Training Efficiency in Intelligent Weed Control Systems [0.0]
  This study presents a new approach for generating synthetic images to improve deep learning-based object detection models for intelligent weed control. Our GenAI-based image generation pipeline integrates the Segment Anything Model (SAM) for zero-shot domain adaptation with a text-to-image Stable Diffusion Model. We evaluate these synthetic datasets using lightweight YOLO models, measuring data efficiency with mAP50 and mAP50-95 scores.
  arXiv  Detail & Related papers  (2024-11-01T12:58:27Z)
• Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization [62.157627519792946]
  We introduce a novel framework called bridged transfer, which initially employs synthetic images for fine-tuning a pre-trained model to improve its transferability. We propose dataset style inversion strategy to improve the stylistic alignment between synthetic and real images. Our proposed methods are evaluated across 10 different datasets and 5 distinct models, demonstrating consistent improvements.
  arXiv  Detail & Related papers  (2024-03-28T22:25:05Z)
• Deep Domain Adaptation: A Sim2Real Neural Approach for Improving Eye-Tracking Systems [80.62854148838359]
  Eye image segmentation is a critical step in eye tracking that has great influence over the final gaze estimate. We use dimensionality-reduction techniques to measure the overlap between the target eye images and synthetic training data. Our methods result in robust, improved performance when tackling the discrepancy between simulation and real-world data samples.
  arXiv  Detail & Related papers  (2024-03-23T22:32:06Z)
• Optimizations of Autoencoders for Analysis and Classification of Microscopic In Situ Hybridization Images [68.8204255655161]
  We propose a deep-learning framework to detect and classify areas of microscopic images with similar levels of gene expression. The data we analyze requires an unsupervised learning model for which we employ a type of Artificial Neural Network - Deep Learning Autoencoders.
  arXiv  Detail & Related papers  (2023-04-19T13:45:28Z)
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images [53.29794593104923]
  We present a novel concept of shared-context processing for whole slide histopathology images. AMIGO uses the celluar graph within the tissue to provide a single representation for a patient. We show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data.
  arXiv  Detail & Related papers  (2023-03-01T23:37:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.