Deep Residual Learning for Image Recognition
In a nutshellResidual connections make very deep neural networks easier to optimize. Instead of learning an entire transformation, layers learn a change relative to their input.
Computer vision
RESEARCH AUTHOR
Jian Sun
Jian Sun is a credited coauthor of “Deep Residual Learning for Image Recognition”. Explore the papers, research findings, and collaborators represented in this collection.
Papers & publications
1 in this collectionRead the original papers, explore an overview, and collect ideas for your own research.
EXPLORE THE WORK
Research in focus
Deep Residual Learning for Image Recognition
Residual networks are compared with plain networks on image classification, with additional evaluation of transferred representations for object detection.
- Residual learning enables effective training of substantially deeper networks.
- The authors evaluate networks with up to 152 layers on ImageNet.
- The learned representations also improve object detection results.
Reading context: Greater depth still has a computational cost. The reported vision benchmarks do not establish improvements for every architecture or application.
Read the original on arXiv ↗