Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun · · 2016
DOI: 10.1109/cvpr.2016.90
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers - 8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Last synced
ACM International Conference on Information and Knowledge Management (CIKM) 2026 · 12 citations
ACM International Conference on Multimedia (ACM MM) 2026 · 6 citations
ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026 · 5 citations
The International Journal of Robotics Research 2026 · 5 citations
ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026 · 4 citations
ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026 · 3 citations
ACM International Conference on Multimedia (ACM MM) 2026 · 1 citations
ACM International Conference on Information and Knowledge Management (CIKM) 2026 · 1 citations
ACM International Conference on Multimedia (ACM MM) 2026 · 1 citations
Sensors 2026 · 0 citations
Tsinghua Science & Technology 2026 · 0 citations
Discover Artificial Intelligence 2026 · 0 citations
Journal of Imaging 2026 · 0 citations
Journal of Imaging 2026 · 0 citations
Mathematics 2026 · 0 citations
ACM International Conference on Multimedia (ACM MM) 2026 · 0 citations
Engineering Applications of Artificial Intelligence 2026 · 0 citations
ETRI Journal 2026 · 0 citations
PLoS ONE 2026 · 0 citations
bioRxiv (Cold Spring Harbor Laboratory) 2026 · 0 citations
No comments yet — start the discussion below.