LLA: Loss-aware Label Assignment for Dense Pedestrian Detection
This project provides an implementation for "LLA: Loss-aware Label Assignment for Dense Pedestrian Detection" on PyTorch.
LLA is the first one-stage detector that surpasses two-stage detectors (e.g., Faster R-CNN) on CrowdHuman dataset. Experiments in the paper were conducted on the internal framework, thus we reimplement them on cvpods and report details as below.
Requirements
Get Started
- install cvpods locally (requires cuda to compile)
python3 -m pip install 'git+https://github.com/Megvii-BaseDetection/cvpods.git'
# (add --user if you don't have permission)
# Or, to install it from a local clone:
git clone https://github.com/Megvii-BaseDetection/cvpods.git
python3 -m pip install -e cvpods
# Or,
pip install -r requirements.txt
python3 setup.py build develop
- prepare datasets
cd /path/to/cvpods/datasets
ln -s /path/to/your/crowdhuman/dataset crowdhuman
- Train & Test
git clone https://github.com/Megvii-BaseDetection/LLA.git
cd LLA/playground/detection/crowdhuman/lla.res50.fpn.crowdhuman.800size.30k # for example
# Train
pods_train --num-gpus 8
# Test
pods_test --num-gpus 8 \
MODEL.WEIGHTS /path/to/your/save_dir/ckpt.pth # optional
OUTPUT_DIR /path/to/your/save_dir # optional
# Multi node training
## sudo apt install net-tools ifconfig
pods_train --num-gpus 8 --num-machines N --machine-rank 0/1/.../N-1 --dist-url "tcp://MASTER_IP:port"
Results on CrowdHuman val set
| Model | Backbone | LR Sched. | Aux. Branch | NMS Thr. | MR | AP50 | Recall | Download |
|---|---|---|---|---|---|---|---|---|
| FCOS | Res50 | 30k | CenterNess | 0.6 | 54.4 | 86.0 | 94.1 | weights |
| ATSS | Res50 | 30k | CenterNess | 0.6 | 49.4 | 87.3 | 94.1 | weights |
| Faster R-CNN | Res50 | 30k | - | 0.5 | 48.5 | 84.3 | 87.1 | weights |
| LLA.FCOS | Res50 | 30k | IoU | 0.6 | 47.5 | 88.2 | 94.4 | weights |
Acknowledgement
This repo is developed based on cvpods. Please check cvpods for more details and features.
License
This repo is released under the Apache 2.0 license. Please see the LICENSE file for more information.
Citing
If you use this work in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:
@article{ge2021lla,
title={LLA: Loss-aware Label Assignment for Dense Pedestrian Detection},
author={Ge, Zheng and Wang, Jianfeng and Huang, Xin and Liu, Songtao and Yoshie, Osamu},
journal={arXiv preprint arXiv:2101.04307},
year={2021}
}
363 Dec 28, 2022
21 Apr 9, 2022
41 Dec 25, 2022
27 Jun 28, 2022
112 Nov 28, 2022
49 Nov 10, 2022
4 May 8, 2022
77 Dec 16, 2022
23 Nov 29, 2022
217 Jan 3, 2023
1k Dec 31, 2022
49 Dec 1, 2022
225 Dec 29, 2022
3 Sep 3, 2022
3.9k Jan 5, 2023
59 Dec 17, 2022
367 Dec 27, 2022
29 Sep 2, 2022
109 Dec 23, 2022