Architecture | 1x1 Convolution, ASPP, Batch Normalization, Dilated Convolution, ResNet |
---|---|
Max Iter | 90000 |
SHOW MORE |
Architecture | 1x1 Convolution, ASPP, Batch Normalization, Dilated Convolution |
---|---|
ID | 28041665 |
SHOW MORE |
DeepLabv3 is a semantic segmentation architecture that improves upon DeepLabv2 with several modifications.To handle the problem of segmenting objects at multiple scales, modules are designed which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, the Atrous Spatial Pyramid Pooling module from DeepLabv2 augmented with image-level features encoding global context and further boost performance.
Model evaluation can be done as follows:
cd /path/to/detectron2/projects/DeepLab
python train_net.py --config-file configs/Cityscapes-SemanticSegmentation/deeplab_v3_plus_R_103_os16_mg124_poly_90k_bs16.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint
To train a model with 8 GPUs run:
cd /path/to/detectron2/projects/DeepLab
python train_net.py --config-file configs/Cityscapes-SemanticSegmentation/deeplab_v3_plus_R_103_os16_mg124_poly_90k_bs16.yaml --num-gpus 8
You can follow the Getting Started guide on Colab to see how to train a model.
You can also read the official Detectron2 documentation.
@article{deeplabv32018,
title={Rethinking atrous convolution for semantic image segmentation},
author={Chen, Liang-Chieh and Papandreou, George and Schroff, Florian and Adam, Hartwig},
journal={arXiv:1706.05587},
year={2017}
}
BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
---|---|---|---|---|
Cityscapes val | DeepLabV3 (R103-DC5) | mIoU | 78.5 | # 3 |
Cityscapes val | DeepLabV3 (R101-DC5) | mIoU | 76.7 | # 5 |