Tianheng Cheng, Xinggang Wang†, Shaoyu Chen, Wenqiang Zhang, Qian Zhang, Chang Huang, Zhaoxiang Zhang, Wenyu Liu
(†: corresponding author)
This is an implementation of SparseInst based on MMDetection, MMCV, and MMEngine.
SparseInst is a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. In contrast to region boxes or anchors (centers), SparseInst adopts a sparse set of instance activation maps as object representation, to highlight informative regions for each foreground objects. Then it obtains the instance-level features by aggregating features according to the highlighted regions for recognition and segmentation. The bipartite matching compels the instance activation maps to predict objects in a one-to-one style, thus avoiding non-maximum suppression (NMS) in post-processing. Owing to the simple yet effective designs with instance activation maps, SparseInst has extremely fast inference speed and achieves 40 FPS and 37.9 AP on COCO (NVIDIA 2080Ti), significantly outperforms the counter parts in terms of speed and accuracy.
In MMDetection's root directory, run the following command to train the model:
python tools/train.py projects/SparseInst/configs/sparseinst_r50_iam_8xb8-ms-270k_coco.py
For multi-gpu training, run:
python -m torch.distributed.launch --nnodes=1 --node_rank=0 --nproc_per_node=${NUM_GPUS} --master_port=29506 --master_addr="127.0.0.1" tools/train.py projects/SparseInst/configs/sparseinst_r50_iam_8xb8-ms-270k_coco.py
In MMDetection's root directory, run the following command to test the model:
python tools/test.py projects/SparseInst/configs/sparseinst_r50_iam_8xb8-ms-270k_coco.py ${CHECKPOINT_PATH}
Here we provide the baseline version of SparseInst with ResNet50 backbone.
To find more variants, please visit the official model zoo.
Backbone | Style | Lr schd | Mem (GB) | FPS | mask AP val2017 | Config | Download |
---|---|---|---|---|---|---|---|
R-50 | PyTorch | 270k | 8.7 | 44.3 | 32.9 | config | model | log |
If you find SparseInst is useful in your research or applications, please consider giving a star 🌟 to the official repository and citing SparseInst by the following BibTeX entry.
@inproceedings{Cheng2022SparseInst,
title = {Sparse Instance Activation for Real-Time Instance Segmentation},
author = {Cheng, Tianheng and Wang, Xinggang and Chen, Shaoyu and Zhang, Wenqiang and Zhang, Qian and Huang, Chang and Zhang, Zhaoxiang and Liu, Wenyu},
booktitle = {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},
year = {2022}
}
-
Milestone 1: PR-ready, and acceptable to be one of the
projects/
.-
Finish the code
-
Basic docstrings & proper citation
-
Test-time correctness
-
A full README
-
-
Milestone 2: Indicates a successful model implementation.
-
Training-time correctness
-
-
Milestone 3: Good to be a part of our core package!
-
Type hints and docstrings
-
Unit tests
-
Code polishing
-
Metafile.yml
-
-
Move your modules into the core package following the codebase's file hierarchy structure.
-
Refactor your modules into the core package following the codebase's file hierarchy structure.