SCALoss
PyTorch implementation of the paper "SCALoss: Side and Corner Aligned Loss for Bounding Box Regression" (AAAI 2022).
Introduction
- IoU-based loss has the gradient vanish problem in the case of low overlapping bounding boxes with slow convergence speed.
- Side Overlap can put more penalty for low overlapping bounding box cases and Corner Distance can speed up the convergence.
- SCALoss, which combines Side Overlap and Corner Distance, can serve as a comprehensive similarity measure, leading to better localization performance and faster convergence speed.
Prerequisites
- Python>=3.6.0
- PyTorch>=1.7
- Other dependencies described in requirements.txt
Install
Conda is not necessary for the installation. Nevertheless, the installation process here is described using it.
$ conda create -n sca-yolo python=3.8 -y
$ conda activate sca-yolo
$ git clone https://github.com/Turoad/SCALoss
$ cd SCALoss
$ pip install -r requirements.txt
Getting started
Train a model:
python train.py --data [dataset config] --cfg [model config] --weights [path of pretrain weights] --batch-size [batch size num]
For example, to train yolov3-tiny on COCO dataset from scratch with batch size=128.
python train.py --data coco.yaml --cfg yolov3-tiny.yaml --weights '' --batch-size 128
For multi-gpu training, it is recommended to use:
python -m torch.distributed.launch --nproc_per_node 4 train.py --img 640 --batch 32 --epochs 300 --data coco.yaml --weights '' --cfg yolov3.yaml --device 0,1,2,3
Test a model:
python val.py --data coco.yaml --weights runs/train/exp15/weights/last.pt --img 640 --iou-thres=0.65
Results and Checkpoints
YOLOv3-tiny
| Model | mAP 0.5:0.95 |
AP 0.5 |
AP 0.65 |
AP 0.75 |
AP 0.8 |
AP 0.9 |
|---|---|---|---|---|---|---|
| IoU | 18.8 | 36.2 | 27.2 | 17.3 | 11.6 | 1.9 |
| GIoU relative improv.(%) |
18.8 0% |
36.2 0% |
27.1 -0.37% |
17.6 1.73% |
11.8 1.72% |
2.1 10.53% |
| DIoU relative improv.(%) |
18.8 0% |
36.4 0.55% |
26.9 -1.1% |
17.2 -0.58% |
11.8 1.72% |
1.9 0% |
| CIoU relative improv.(%) |
18.9 0.53% |
36.6 1.1% |
27.3 0.37% |
17.2 -0.58% |
11.6 0% |
2.1 10.53% |
| SCA relative improv.(%) |
19.9 5.85% |
36.6 1.1% |
28.3 4.04% |
19.1 10.4% |
13.3 14.66% |
2.7 42.11% |
The convergence curves of different losses on YOLOV3-tiny: 
YOLOv3
| Model | mAP 0.5:0.95 |
AP 0.5 |
AP 0.65 |
AP 0.75 |
AP 0.8 |
AP 0.9 |
|---|---|---|---|---|---|---|
| IoU | 44.8 | 64.2 | 57.5 | 48.8 | 41.8 | 20.7 |
| GIoU relative improv.(%) |
44.7 -0.22% |
64.4 0.31% |
57.5 0% |
48.5 -0.61% |
42 0.48% |
20.4 -1.45% |
| DIoU relative improv.(%) |
44.7 -0.22% |
64.3 0.16% |
57.5 0% |
48.9 0.2% |
42.1 0.72% |
19.8 -4.35% |
| CIoU relative improv.(%) |
44.7 -0.22% |
64.3 0.16% |
57.5 0% |
48.9 0.2% |
41.7 -0.24% |
19.8 -4.35% |
| SCA relative improv.(%) |
45.3 1.12% |
64.1 -0.16% |
57.9 0.7% |
49.9 2.25% |
43.3 3.59% |
21.4 3.38% |
YOLOV5s
comming soon
Citation
If our paper and code are beneficial to your work, please consider citing:
@inproceedings{zheng2022scaloss,
title={SCALoss: Side and Corner Aligned Loss for Bounding Box Regression},
author={Zheng, Tu and Zhao, Shuai and Liu, Yang and Liu, Zili and Cai, Deng},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
year={2022}
}
Acknowledgement
The code is modified from ultralytics/yolov3.
71 Dec 4, 2022
1 Jan 18, 2022
44 Dec 17, 2022
50 Nov 26, 2022
11 Nov 19, 2022
115 Dec 23, 2022
48 Nov 14, 2022
53 Dec 20, 2022
112 Jan 01, 2023
503 Jan 04, 2023
27 Sep 14, 2022
142 Jan 04, 2023
23 Sep 10, 2022
6 May 11, 2021
42 Nov 10, 2022
2 Dec 21, 2021
39 Dec 28, 2022
1 Jan 20, 2022
2.9k Jan 03, 2023
4 Sep 08, 2022
830 Jan 03, 2023
2 Oct 20, 2022
1 Sep 10, 2022
130 Jan 02, 2023
89 Dec 10, 2022
190 Dec 01, 2022
8 Feb 23, 2021
1 Mar 08, 2022