Translations:Deep Residual Learning for Image Recognition/7/en

• Residual learning framework: A reformulation where network layers learn residual functions $ F(x) = H(x) - x $ rather than unreferenced mappings $ H(x) $, with identity shortcut connections passing the input directly to deeper layers.
• Extremely deep networks: Successful training of networks with 152 layers for ImageNet and over 1,000 layers on CIFAR-10, far exceeding the depth of prior architectures.
• State-of-the-art results: First place in the ILSVRC 2015 classification, detection, and localization tracks, as well as first place in the COCO 2015 detection and segmentation tracks.
• Generalizable insight: The residual learning principle proved applicable far beyond image classification, influencing architectures across all areas of deep learning.