-**Totally box-free:** SOLO is totally box-free thus not being restricted by (anchor) box locations and scales, and naturally benefits from the inherent advantages of FCNs.
-**Direct instance segmentation:** Our method takes an image as input, directly outputs instance masks and corresponding class probabilities, in a fully convolutional, box-free and grouping-free paradigm.
-**High-quality mask prediction:** SOLOv2 is able to predict fine and detailed masks, especially at object boundaries.
-**State-of-the-art performance:** Our best single model based on ResNet-101 and deformable convolutions achieves **41.7%** in AP on COCO test-dev (without multi-scale testing). A light-weight version of SOLOv2 executes at **31.3** FPS on a single V100 GPU and yields **37.1%** AP.
| 软件 | 版本 |
| :------: | :------: |
| DTK | 25.04.1 |
| python | 3.11 |
| torch | 2.4.1+das.opt1.dtk25041 |
## Updates
- SOLOv2 implemented on detectron2 is released at [adet](https://github.com/aim-uofa/AdelaiDet/blob/master/configs/SOLOv2/README.md). (07/12/20)
- Training speeds up (~1.7x faster) for all models. (03/12/20)
- SOLOv2 is available. Code and trained models of SOLOv2 are released. (08/07/2020)
- Light-weight models and R101-based models are available. (31/03/2020)
- SOLOv1 is available. Code and trained models of SOLO and Decoupled SOLO are released. (28/03/2020)
推荐使用镜像:
- 挂载地址 `-v` 根据实际模型情况修改
## Installation
This implementation is based on [mmdetection](https://github.com/open-mmlab/mmdetection)(v1.0.0). Please refer to [INSTALL.md](docs/INSTALL.md) for installation and dataset preparation.
## Models
For your convenience, we provide the following trained models on COCO (more models are coming soon).
If you need the models in [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) framework, please refer to [paddlepaddle/README.md](./paddlepaddle/README.MD).
Model | Multi-scale training | Testing time / im | AP (minival) | Link
--- |:---:|:---:|:---:|:---:
SOLO_R50_1x | No | 77ms | 32.9 | [download](https://huggingface.co/xinlongwang/SOLO/resolve/main/SOLO_R50_1x.pth?download=true)
For academic use, this project is licensed under the 2-clause BSD License - see the LICENSE file for details. For commercial use, please contact [Xinlong Wang](https://www.xloong.wang/) and [Chunhua Shen](https://cs.adelaide.edu.au/~chhshen/).
-**Totally box-free:** SOLO is totally box-free thus not being restricted by (anchor) box locations and scales, and naturally benefits from the inherent advantages of FCNs.
-**Direct instance segmentation:** Our method takes an image as input, directly outputs instance masks and corresponding class probabilities, in a fully convolutional, box-free and grouping-free paradigm.
-**High-quality mask prediction:** SOLOv2 is able to predict fine and detailed masks, especially at object boundaries.
-**State-of-the-art performance:** Our best single model based on ResNet-101 and deformable convolutions achieves **41.7%** in AP on COCO test-dev (without multi-scale testing). A light-weight version of SOLOv2 executes at **31.3** FPS on a single V100 GPU and yields **37.1%** AP.
## Updates
- SOLOv2 implemented on detectron2 is released at [adet](https://github.com/aim-uofa/AdelaiDet/blob/master/configs/SOLOv2/README.md). (07/12/20)
- Training speeds up (~1.7x faster) for all models. (03/12/20)
- SOLOv2 is available. Code and trained models of SOLOv2 are released. (08/07/2020)
- Light-weight models and R101-based models are available. (31/03/2020)
- SOLOv1 is available. Code and trained models of SOLO and Decoupled SOLO are released. (28/03/2020)
## Installation
This implementation is based on [mmdetection](https://github.com/open-mmlab/mmdetection)(v1.0.0). Please refer to [INSTALL.md](docs/INSTALL.md) for installation and dataset preparation.
## Models
For your convenience, we provide the following trained models on COCO (more models are coming soon).
If you need the models in [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) framework, please refer to [paddlepaddle/README.md](./paddlepaddle/README.MD).
Model | Multi-scale training | Testing time / im | AP (minival) | Link
--- |:---:|:---:|:---:|:---:
SOLO_R50_1x | No | 77ms | 32.9 | [download](https://huggingface.co/xinlongwang/SOLO/resolve/main/SOLO_R50_1x.pth?download=true)
title={SOLOv2: Dynamic and Fast Instance Segmentation},
author={Wang, Xinlong and Zhang, Rufeng and Kong, Tao and Li, Lei and Shen, Chunhua},
journal={Proc. Advances in Neural Information Processing Systems (NeurIPS)},
year={2020}
}
```
## License
For academic use, this project is licensed under the 2-clause BSD License - see the LICENSE file for details. For commercial use, please contact [Xinlong Wang](https://www.xloong.wang/) and [Chunhua Shen](https://cs.adelaide.edu.au/~chhshen/).
