Weight Standardization

Siyuan QiaoHuiyu WangChenxi LiuWei ShenAlan Yuille

   Papers with code   Abstract  PDF

In this paper, we propose Weight Standardization (WS) to accelerate deep network training. WS is targeted at the micro-batch training setting where each GPU typically has only 1-2 images for training... (read more)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
Mask R-CNN
(ResNeXt-101 32x4d-FPN…)
0.433
--
2
Mask R-CNN
(ResNet-50-FPN, GN+WS,…)
0.410
--
3
Mask R-CNN
(ResNet-50-FPN, GN+WS,…)
0.402
--
4
Faster R-CNN
(ResNet-50-FPN, GN+WS,…)
0.389
--