SparseInst ?

A simple framework for real-time instance segmentation, CVPR 2022 by Tianheng Cheng, Xinggang Wang, Shaoyu Chen, Wenqiang Zhang, Qian Zhang, Chang Huang, Zhaoxiang Zhang, Wenyu Liu (: corresponding author)


  • SparseInst presents a new object representation method, i.e., Instance Activation Maps (IAM), to adaptively highlight informative regions of objects for recognition.
  • SparseInst is a simple, efficient, and fully convolutional framework without non-maximum suppression (NMS) or sorting, and easy to deploy!
  • SparseInst achieves good trade-off between speed and accuracy, e.g., 37.9 AP and 40 FPS with 608x input.


This project is under active development, please stay tuned!

  • [2022-3-25]: We have released the code and models for SparseInst!


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.


We provide two versions of SparseInst, i.e., the basic IAM (3×3 convolution) and the Group IAM (G-IAM for short), with different backbones. All models are trained on MS-COCO train2017.

Fast models

model backbone input aug APval AP FPS weights
SparseInst R-50 640 32.8 44.3 model
SparseInst R-50-vd 640 34.1 42.6 model
SparseInst (G-IAM) R-50 608 33.4 44.6 model
SparseInst (G-IAM) R-50 608 34.2 34.7 44.6 model
SparseInst (G-IAM) R-50-DCN 608 36.4 36.8 41.6 model
SparseInst (G-IAM) R-50-vd 608 35.6 36.1 42.8 model
SparseInst (G-IAM) R-50-vd-DCN 608 37.4 37.9 40.0 model
SparseInst (G-IAM) R-50-vd-DCN 640 37.7 38.1 39.3 model


  • We will continue adding more models including more efficient convolutional networks, vision transformers, and larger models for high performance and high speed, please stay tuned ?!
  • Inference speeds are measured on one NVIDIA 2080Ti.
  • We haven’t adopt TensorRT or other tools to accelerate the inference of SparseInst. However, we are working on it now and will provide support for ONNX, TensorRT, MindSpore, Blade, and other frameworks as soon as possible!
  • AP denotes AP evaluated on MS-COCO test-dev2017
  • input denotes the shorter side of the input, e.g., 512×864 and 608×864, we keep the aspect ratio of the input and the longer side is no more than 864.
  • The inference speed might slightly change on different machines (2080 Ti) and different versions of detectron (we mainly use v0.3). If the change is sharp, e.g., > 5ms, please feel free to contact us.
  • For aug (augmentation), we only adopt the simple random crop (crop size: [384, 600]) provided by detectron2.
  • We adopt weight decay=5e-2 as default setting, which is slightly different from the original paper.

Installation and Prerequisites

This project is built upon the excellent framework detectron2, and you should install detectron2 first, please check official installation guide for more details.

Note: we mainly use v0.3 of detectron2 for experiments and evaluations. Besides, we also test our code on the newest version v0.6. If you find some bugs or incompatibility problems of higher version of detectron2, please feel free to raise a issue!

Install the detectron2:

git clone
# if you swith to a specific version, e.g., v0.3 (recommended)
git checkout tags/v0.3
# build detectron2
python build develop

Getting Start

Testing SparseInst

Before testing, you should specify the config file <CONFIG> and the model weights <MODEL-PATH>. In addition, you can change the input size by setting the INPUT.MIN_SIZE_TEST in both config file or commandline.

  • [Performance Evaluation] To obtain the evaluation results, e.g., mask AP on COCO, you can run:

python --config-file <CONFIG> --num-gpus <GPUS> --eval MODEL.WEIGHTS <MODEL-PATH>
# example:
python --config-file configs/sparse_inst_r50_giam.yaml --num-gpus 8 --eval MODEL.WEIGHTS sparse_inst_r50_giam_aug_2b7d68.pth
  • [Inference Speed] To obtain the inference speed (FPS) on one GPU device, you can run:

# example:
python --config-file configs/sparse_inst_r50_giam.yaml MODEL.WEIGHTS sparse_inst_r50_giam_aug_2b7d68.pth INPUT.MIN_SIZE_TEST 512


  • The only supports 1 GPU and 1 image per batch for measuring inference speed.
  • The inference time consists of the pure forward time and the post-processing time. While the evaluation processing, data loading, and pre-processing for wrappers (e.g., ImageList) are not included.
  • COCOMaskEvaluator is modified from COCOEvaluator for evaluating mask-only results.

Training SparseInst

To train the SparseInst model on COCO dataset with 8 GPUs. 8 GPUs are required for the training. If you only have 4 GPUs or GPU memory is limited, it doesn’t matter and you can reduce the batch size through SOLVER.IMS_PER_BATCH or reduce the input size. If you adjust the batch size, learning schedule should be adjusted according to the linear scaling rule.

python --config-file <CONFIG> --num-gpus 8 
# example
python --config-file configs/sparse_inst_r50vd_dcn_giam_aug.yaml --num-gpus 8


SparseInst is based on detectron2, OneNet, DETR, and timm, and we sincerely thanks for their code and contribution to the community!

Citing SparseInst

If you find SparseInst is useful in your research or applications, please consider giving us a star ? and citing SparseInst by the following BibTeX entry.

  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}


SparseInst is released under the MIT Licence.


View Github