Methods › Computer Vision › Convolutional Neural Networks › ResNet-RS
ResNet-RS
Introduced by Irwan Bello et al. in Revisiting ResNets: Improved Training and Scaling Strategies
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ResNet-RS is a family of ResNet architectures that are 1.7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet. The authors propose two new scaling strategies: (1) scale model depth in regimes where overfitting can occur (width scaling is preferable otherwise); (2) increase image resolution more slowly than previously recommended.
Additional improvements include the use of a cosine learning rate schedule, label smoothing, stochastic depth, RandAugment, decreased weight decay, squeeze-and-excitation and the use of the ResNet-D architecture.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Revisiting 3D ResNets for Video Recognition 3 Sep 2021 · 5 repositories · arXiv:2109.01696
-
Revisiting ResNets: Improved Training and Scaling Strategies 13 Mar 2021 · 3 repositories · arXiv:2103.07579
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Action Classification | 2 |
| Contrastive Learning | 1 |
| Document Image Classification | 1 |
| Image Classification | 1 |
| Semantic Object Interaction Classification | 1 |
| Video Classification | 1 |
| Video Recognition | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections