This file provides Mask R-CNN baseline results and models trained with Group Normalization:
@article{GroupNorm2018,
title={Group Normalization},
author={Yuxin Wu and Kaiming He},
journal={arXiv:1803.08494},
year={2018}
}
Note: This code uses the GroupNorm op implemented in CUDA, included in the Caffe2 repo. When writing this document, Caffe2 is being merged into PyTorch, and the GroupNorm op is located here. Make sure your Caffe2 is up to date.
These models are trained in Caffe2 on the standard ImageNet-1k dataset, using GroupNorm with 32 groups (G=32).
- R-50-GN.pkl: ResNet-50 with GN, 24.0% top-1 error (center-crop).
- R-101-GN.pkl: ResNet-101 with GN, 22.6% top-1 error (center-crop).
| case | type | lr schd |
im/ gpu |
train mem (GB) |
train time (s/iter) |
train time total (hr) |
inference time (s/im) |
box AP |
mask AP |
model id |
|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN, BN* | Mask R-CNN | 2x | 2 | 8.6 | 0.897 | 44.9 | 0.099 + 0.018 | 38.6 | 34.5 | 35859007 |
| R-101-FPN, BN* | Mask R-CNN | 2x | 2 | 10.2 | 0.993 | 49.7 | 0.126 + 0.017 | 40.9 | 36.4 | 35861858 |
Notes:
- This table is copied from Detectron Model Zoo.
- BN* means that BatchNorm (BN) is used for pre-training and is frozen and turned into a per-channel linear layer when fine-tuning. This is the default of Faster/Mask R-CNN and Detectron.
| case | type | lr schd |
im/ gpu |
train mem (GB) |
train time (s/iter) |
train time total (hr) |
inference time (s/im) |
box AP |
mask AP |
model id | download links |
|---|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN, GN | Mask R-CNN | 2x | 2 | 10.5 | 1.017 | 50.8 | 0.146 + 0.017 | 40.3 | 35.7 | 48616381 | model | boxes | masks |
| R-101-FPN, GN | Mask R-CNN | 2x | 2 | 12.4 | 1.151 | 57.5 | 0.180 + 0.015 | 41.8 | 36.8 | 48616724 | model | boxes | masks |
Notes:
- GN is applied on: (i) ResNet layers inherited from pre-training, (ii) the FPN-specific layers, (iii) the RoI bbox head, and (iv) the RoI mask head.
- These GN models use a 4conv+1fc RoI box head. The BN* counterpart with this head performs similarly with the default 2fc head: using this codebase, R-50-FPN BN* with 4conv+1fc has 38.8/34.4 box/mask AP.
- 2x is the default schedule (180k) in Detectron.
| case | type | lr schd |
im/ gpu |
train mem (GB) |
train time (s/iter) |
train time total (hr) |
inference time (s/im) |
box AP |
mask AP |
model id | download links |
|---|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN, GN | Mask R-CNN | 3x | 2 | 10.5 | 1.033 | 77.4 | 0.145 + 0.015 | 40.8 | 36.1 | 48734751 | model | boxes | masks |
| R-101-FPN, GN | Mask R-CNN | 3x | 2 | 12.4 | 1.171 | 87.9 | 0.180 + 0.014 | 42.3 | 37.2 | 48734779 | model | boxes | masks |
Notes:
- 3x is a longer schedule (270k). GN can improve further when using the longer schedule, but its BN* counterpart remains similar (R-50-FPN BN*: 38.9/34.3) with the longer schedule.
- These models are without any scale augmentation that can further improve results.
GN enables to train Mask R-CNN from scratch without ImageNet pre-training, despite the small batch size.
| case | type | lr schd |
im/ gpu |
train mem (GB) |
train time (s/iter) |
train time total (hr) |
inference time (s/im) |
box AP |
mask AP |
model id |
|---|---|---|---|---|---|---|---|---|---|---|
| R-50-FPN, GN, scratch | Mask R-CNN | 3x | 2 | 10.8 | 1.087 | 81.5 | 0.140 + 0.019 | 39.5 | 35.2 | 56421872 |
| R-101-FPN, GN, scratch | Mask R-CNN | 3x | 2 | 12.7 | 1.243 | 93.2 | 0.177 + 0.019 | 41.0 | 36.4 | 56421911 |
Notes:
- To reproduce these results, see the config yaml files starting with
scratch. - These are results using
freeze_at=0. See this commit about the related issue.
Notes:
- These are early results that followed the default training using
freeze_at=2. This means the layers of conv1 and res2 were simply random weights in the case of training from-scratch. See this commit about the related issue.