Training convolutional neural networks with megapixel images

2018/04/16 by Hans Pinckaers, Pinckaers, Hans, Geert Litjens +1 · 1 citation
Computer Science · Engineering · #AI in cancer detection #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing Techniques and Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.1804.05712

Submitted to MIDL 2018

arxiv created 2018/04/16 · openalex publication_date 2018/04/16 · arxiv updated 2018/04/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

To train deep convolutional neural networks, the input data and the intermediate activations need to be kept in memory to calculate the gradient descent step. Given the limited memory available in the current generation accelerator cards, this limits the maximum dimensions of the input data. We demonstrate a method to train convolutional neural networks holding only parts of the image in memory while giving equivalent results. We quantitatively compare this new way of training convolutional neural networks with conventional training. In addition, as a proof of concept, we train a convolutional neural network with 64 megapixel images, which requires 97% less memory than the conventional approach.

Cited by

• C2G-Net: Exploiting Morphological Properties for Image Classification

Related

• Fast Training of Convolutional Neural Networks via Kernel Rescaling
• Reversible designs for extreme memory cost reduction of CNN training
• One weird trick for parallelizing convolutional neural networks
• Exploring the Potential of Low-bit Training of Convolutional Neural Networks
• Survey on Large Scale Neural Network Training