Deep Residual Learning for Image Recognition (ResNet)
Kaiming He, Xiangyu Zhang, Shaoqing Ren and Jian Sun submitted Deep Residual Learning for Image Recognition on December 10, 2015. The paper presents a residual learning framework that reformulates layers as learning residual functions with reference to layer inputs and reports experiments with residual networks up to 152 layers on ImageNet.
Historical classification
This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.
Why it matters
A documented deep-learning research milestone for the residual-learning framework later published at CVPR 2016, recorded here at the paper-submission level rather than as an invention or system-birth date.
People, organizations & technologies
PEOPLE
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
TECHNOLOGIES
Residual learning, Residual network, ResNet
Evidence & verification
STATE
verified
CONFIDENCE
high
LAST VERIFIED
2026-09-14T17:08:05+08:00
Title, authors, December 10 2015 submission date, residual-learning formulation and reported 152-layer ImageNet experiments are supported by the original arXiv record. The Computer Vision Foundation's CVPR 2016 record independently corroborates the authors, paper, framework and later conference publication. Microsoft Research additionally records the same paper and authors as a CVPR publication in June 2016. The day-precision date is attached specifically to the arXiv submission milestone, not asserted as an invention, architecture-birth, development-start, or software-release date. No universal priority, ancestry, influence, causality, institutional affiliation or geography is inferred.
Sources
Deep Residual Learning for Image Recognition
arXiv
PUBLISHED
2015-12-10
Deep Residual Learning for Image Recognition
Computer Vision Foundation / CVPR
Deep Residual Learning for Image Recognition
Microsoft Research
Trace the chronology
Record identity
LINEAiGE IDresnet-2015