| Training Techniques | Weight Decay, SGD with Momentum |
|---|---|
| Architecture | RPN, RoIAlign, FPN, Feedforward Network, 1x1 Convolution, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax, Non Maximum Suppression |
| ID | maskrcnn_resnet50_fpn |
| SHOW MORE |
Mask R-CNN extends Faster R-CNN to solve instance segmentation tasks. It achieves this by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. In principle, Mask R-CNN is an intuitive extension of Faster R-CNN, but constructing the mask branch properly is critical for good results.
Most importantly, Faster R-CNN was not designed for pixel-to-pixel alignment between network inputs and outputs. This is evident in how RoIPool, the de facto core operation for attending to instances, performs coarse spatial quantization for feature extraction. To fix the misalignment, Mask R-CNN utilises a simple, quantization-free layer, called RoIAlign, that faithfully preserves exact spatial locations.
To load a pretrained model:
import torchvision.models as models
maskrcnn_resnet50_fpn = models.detection.maskrcnn_resnet50_fpn(pretrained=True)
Replace the model name with the variant you want to use, e.g. maskrcnn_resnet50_fpn. You can find
the IDs in the model summaries at the top of this page.
To evaluate the model, use the object detection recipes from the library.
You can follow the torchvision recipe on GitHub for training a new model afresh.
@article{DBLP:journals/corr/HeGDG17,
author = {Kaiming He and
Georgia Gkioxari and
Piotr Doll{\'{a}}r and
Ross B. Girshick},
title = {Mask {R-CNN}},
journal = {CoRR},
volume = {abs/1703.06870},
year = {2017},
url = {http://arxiv.org/abs/1703.06870},
archivePrefix = {arXiv},
eprint = {1703.06870},
timestamp = {Mon, 13 Aug 2018 16:46:36 +0200},
biburl = {https://dblp.org/rec/journals/corr/HeGDG17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Object Detection
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| COCO minival | Mask R-CNN ResNet-50 FPN | box AP | 37.9 | # 95 |
Instance Segmentation
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| COCO minival | Mask R-CNN ResNet-50 FPN | mask AP | 34.6 | # 52 |
