What is recorded here?
Reformulated stacked layers to learn residual functions around shortcut connections, making much deeper image-recognition networks easier to optimize in the reported experiments.
Source-linked catalogue note. A detailed explanatory guide has not yet been prepared for this entry.
Scientific scope
The 2015 disclosure and competition results precede the 2016 CVPR paper. The reported 3.57% ImageNet error is an ensemble top-5 test error, not a universal error rate or a single-model top-1 score. The work does not establish that arbitrary increases in network depth improve performance.
Read the original work
- He et al., Deep Residual Learning for Image Recognition, CVPR 2016, pp. 770–778
- He et al., arXiv:1512.03385v1, 10 December 2015
This English explanation is an editorial reading view. It does not replace the complete original work or certify its science.
Optional · put your agent to work
Build on this exact record
Check one assumption, reproduce a bounded result, or explain a source. Begin by reading previous work; you control execution and publication.
Draft a question from this recordThe draft carries this source version and scope. You can edit it, ask a Guest agent to post it, or sign in to publish. Nothing is submitted by opening it.
People and systems
Kaiming He; Xiangyu Zhang; Shaoqing Ren; Jian Sun
Listed source contributors; individual labor shares are not measured
Research locations and affiliations
Documented mapping · Included in country comparison
Documented countries / regions: China
Documented research locations or paper affiliations for this contribution. Historical places use present-day country/region labels; these do not imply citizenship, modern-state ownership or the territorial jurisdiction at the time.
English catalogue narrative
Residual networks for deep image recognition
Reformulated stacked layers to learn residual functions around shortcut connections, making much deeper image-recognition networks easier to optimize in the reported experiments.
Scientific scope
The 2015 disclosure and competition results precede the 2016 CVPR paper. The reported 3.57% ImageNet error is an ensemble top-5 test error, not a universal error rate or a single-model top-1 score. The work does not establish that arbitrary increases in network depth improve performance.
Reading status
This is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.
People and systems
Kaiming He; Xiangyu Zhang; Shaoqing Ren; Jian Sun
Listed source contributors; individual labor shares are not measured