CenterGroup

This the official implementation of our ICCV 2021 paper

The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation,
Guillem Brasó, Nikita Kister, Laura Leal-Taixé
We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image. Our approach uses a transformer to obtain context-aware embeddings for all detected keypoints and centers and then applies multi-head attention to directly group joints into their corresponding person centers. While most bottom-up methods rely on non-learnable clustering at inference, CenterGroup uses a fully differentiable attention mechanism that we train end-to-end together with our keypoint detector. As a result, our method obtains state-of-the-art performance with up to 2.5x faster inference time than competing bottom-up methods.

@article{Braso_2021_ICCV,
    author    = {Bras\'o, Guillem and Kister, Nikita and Leal-Taix\'e, Laura},
    title     = {The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation},
    journal = {ICCV},
    year      = {2021}
}

Main Results

With the code contained in this repo, you should be able to reproduce the following results.

Results on COCO val2017

Results on COCO test2017

Results on CrowdPose test

Installation

Please see docs/INSTALL.md

Model Zoo

Please see docs/MODEL_ZOO.md

Evaluation

To evaluate a model you have to specify its configuration file, its checkpoint, and the number of GPUs you want to use. All of our configurations and checkpoints are available here) For example, to run CenterGroup with a HigherHRNet32 detector and a single GPU you can run the following:

NUM_GPUS=1
./tools/dist_test.sh configs/centergroup2/coco/higherhrnet_w32_coco_512x512 models/centergroup/centergroup_higherhrnet_w32_coco_512x512.pth $NUM_GPUS 1234

If you want to use multi-scale testing, please add the --multi-scale flag, e.g.:

./tools/dist_test.sh configs/centergroup2/coco/higherhrnet_w32_coco_512x512 models/centergroup/centergroup_higherhrnet_w32_coco_512x512.pth $NUM_GPUS 1234 --multi-scale

You can also modify any other config entry with the --cfg-options entry. For example, to disable flip-testing, which is used by default, you can run:

./tools/dist_test.sh configs/centergroup2/coco/higherhrnet_w32_coco_512x512 models/centergroup/centergroup_higherhrnet_w32_coco_512x512.pth $NUM_GPUS 1234 --cfg-options model.test_cfg.flip_test=False

You may need to modify the checkpoint's path, depending on where you downloaded it, and the entry data_root in the config file, depending on where you stored your data.

Training HigherHRNet with Centers

TODO

Training CenterGroup

TODO

Demo

TODO

Acknowledgements

Our code is based on mmpose, which reimplemented HigherHRNet's work. We thank the authors of these codebases for their great work!