In subject-driven text-to-image generation, recent works have achieved superior performance by training the model on synthetic datasets containing numerous image pairs. Trained on these datasets, generative models can produce text-aligned images for specific subject from arbitrary testing image in a zero-shot manner. They even outperform methods which require additional fine-tuning on testing images. However, the cost of creating such datasets is prohibitive for most researchers. To generate a single training pair, current methods fine-tune a pre-trained text-to-image model on the subject image to capture fine-grained details, then use the fine-tuned model to create images for the same subject based on creative text prompts. Consequently, constructing a large-scale dataset with millions of subjects can require hundreds of thousands of GPU hours. To tackle this problem, we propose Toffee, an efficient method to construct datasets for subject-driven editing and generation. Specifically, our dataset construction does not need any subject-level fine-tuning. After pre-training two generative models, we are able to generate infinite number of high-quality samples. We construct the first large-scale dataset for subject-driven image editing and generation, which contains 5 million image pairs, text prompts, and masks. Our dataset is 5 times the size of previous largest dataset, yet our cost is tens of thousands of GPU hours lower. To test the proposed dataset, we also propose a model which is capable of both subject-driven image editing and generation. By simply training the model on our proposed dataset, it obtains competitive results, illustrating the effectiveness of the proposed dataset construction framework.
COVID-CT-MD: COVID-19 Computed Tomography (CT) Scan Dataset Applicable in Machine Learning and Deep Learning
Concordia University(康考迪亚大学);McGill University Health Center-Research Institute(麦吉尔大学健康中心研究所);Sunnybrook Health Sciences Centre(桑尼布鲁克健康科学中心);University of Toronto(多伦多大学);University of Montreal(蒙特利尔大学);Iran University of Medical Science(伊朗医科大学)
MIMIR: Deep Regression for Automated Analysis of UK Biobank Body MRI
Department of Surgical Sciences, Uppsala University(乌普萨拉大学外科学系);Department of Information Technology, Uppsala University(乌普萨拉大学信息技术系);Antaros Medical AB
Spontaneous preterm birth prediction using convolutional neural networks
Warsaw University of Technology(华沙理工大学);Fetai Health Ltd.(Fetai Health有限公司);Medical University of Warsaw(华沙医科大学);Ernest Wójcicki Prenatal Medicine Foundation(欧内斯特·沃伊奇基产前医学基金会);Tooploox