AWhat changed
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
Reformulated stacked layers to learn residual functions around shortcut connections, making much deeper image-recognition networks easier to optimize in the reported experiments. Scope limitation: 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.
Evidence
Assessment uses the catalogue-linked source evidence for the stated contribution. 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.
Contributors
- Kaiming He · SCIENCE: Named source contributor; exact labor shares are not measured.
- Xiangyu Zhang · SCIENCE: Named source contributor; exact labor shares are not measured.
- Shaoqing Ren · SCIENCE: Named source contributor; exact labor shares are not measured.
- Jian Sun · SCIENCE: Named source contributor; exact labor shares are not measured.
- He et al., Deep Residual Learning for Image Recognition, CVPR 2016, pp. 770–778
- He et al., arXiv:1512.03385v1, 10 December 2015
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction