Gupta Deepak K, Bamba Udbhav, Thakur Abhishek, Gupta Akash, Agarwal Rohit, Sharan Suraj, Demir Ertugul, Agarwal Krishna, Prasad Dilip K
Transmute AI Lab (Texmin Hub), Indian Institute of Technology, ISM Dhanbad, India.
Bio AI Lab, Department of Computer Science, UiT The Arctic University of Norway, Tromso, Norway.
Sci Data. 2024 Jul 12;11(1):771. doi: 10.1038/s41597-024-03587-4.
Current convolutional neural networks (CNNs) are not designed for large scientific images with rich multi-scale features, such as in satellite and microscopy domain. A new phase of development of CNNs especially designed for large images is awaited. However, application-independent high-quality and challenging datasets needed for such development are still missing. We present the 'UltraMNIST dataset' and associated benchmarks for this new research problem of 'training CNNs for large images'. The dataset is simple, representative of wide-ranging challenges in scientific data, and easily customizable for different levels of complexity, smallest and largest features, and sizes of images. Two variants of the problem are discussed: standard version that facilitates the development of novel CNN methods for effective use of the best available GPU resources and the budget-aware version to promote the development of methods that work under constrained GPU memory. Several baselines are presented and the effect of reduced resolution is studied. The presented benchmark dataset and baselines will hopefully trigger the development of new CNN methods for large scientific images.
当前的卷积神经网络（CNN）并非为具有丰富多尺度特征的大型科学图像而设计，比如卫星和显微镜领域的图像。人们期待着专门为大型图像设计的CNN发展的新阶段。然而，此类发展所需的与应用无关的高质量且具有挑战性的数据集仍然缺失。我们针对“为大型图像训练CNN”这一新研究问题，提出了“超MNIST数据集”及相关基准。该数据集很简单，代表了科学数据中广泛的挑战，并且可以轻松针对不同级别的复杂性、最小和最大特征以及图像大小进行定制。文中讨论了该问题的两种变体：标准版本有助于开发有效利用最佳可用GPU资源的新型CNN方法，以及预算感知版本以促进在有限GPU内存下工作的方法的开发。给出了几个基线，并研究了分辨率降低的影响。所呈现的基准数据集和基线有望引发针对大型科学图像的新CNN方法的开发。
