Keyword

convolutional neural networks

2 papers tagged “convolutional neural networks”

AI2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · Jun 2016 Open access

Deep Residual Learning for Image Recognition

Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun

The authors introduced a residual learning framework that reformulates network layers to learn residual functions with reference to their inputs (via identity 'shortcut' connections), making very deep networks substantially easier to optimize. They showed that such residual networks gain accuracy from greatly increased depth, evaluating models up to 152 layers deep on ImageNet at lower complexity than VGG networks. The approach won first place in the ILSVRC 2015 classification task and yielded large improvements on detection and localization benchmarks.

deep learning computer vision convolutional neural networks image classification

AIMedical Image Computing and Computer-Assisted Intervention (MICCAI 2015), LNCS vol. 9351, pp. 234-241 · Oct 2015 Open access

U-Net: Convolutional Networks for Biomedical Image Segmentation

Olaf Ronneberger, Philipp Fischer and Thomas Brox

The paper introduces U-Net, an encoder-decoder convolutional network with a contracting path to capture context and a symmetric expanding path with skip connections for precise localization. Combined with heavy data augmentation, the architecture trains end-to-end from very few annotated images. It won the ISBI cell-tracking and neuronal-structure segmentation challenges and segments a 512x512 image in under a second on a GPU.

image segmentation convolutional neural networks biomedical imaging deep learning