SCALoss: Side and Corner Aligned Loss for Bounding Box Regression (AAAI2022).

Last update: Sep 07, 2022

Related tags

Deep Learning SCALoss

Overview

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.

An implementation for the loss function proposed in Decoupled Contrastive Loss paper.

Decoupled-Contrastive-Learning This repository is an implementation for the loss function proposed in Decoupled Contrastive Loss paper. Requirements P

71 Dec 4, 2022

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

This is the implementation of "Training deep neural networks via direct loss minimization" published at ICML 2016 in PyTorch. The implementation targe

1 Jan 18, 2022

Official PyTorch implementation of "Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition" in AAAI2022.

AimCLR This is an official PyTorch implementation of "Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Reco

44 Dec 17, 2022

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes (AAAI2022)

SCALoss: Side and Corner Aligned Loss for Bounding Box Regression (AAAI2022).

Related tags

Overview

SCALoss

Introduction

Prerequisites

Install

Getting started

Results and Checkpoints

YOLOv3-tiny

YOLOv3

YOLOV5s

Citation

Acknowledgement

You might also like...

An implementation for the loss function proposed in Decoupled Contrastive Loss paper.

Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

Official PyTorch implementation of "Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition" in AAAI2022.

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes (AAAI2022)

Repository for "Improving evidential deep learning via multi-task learning," published in AAAI2022

Multi-Scale Aligned Distillation for Low-Resolution Detection (CVPR2021)

Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.

Multi-Scale Aligned Distillation for Low-Resolution Detection (CVPR2021)

Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision (ICCV 2021)

Releases(models)

models(Apr 28, 2022)

Owner

TuZheng

Bayesian dessert for Lasagne

Repository for the Bias Benchmark for QA dataset.

Offline Reinforcement Learning with Implicit Q-Learning

Retrieve and analysis data from SDSS (Sloan Digital Sky Survey)

The implementation of "Shuffle Transformer: Rethinking Spatial Shuffle for Vision Transformer"

A web porting for NVlabs' StyleGAN2, to facilitate exploring all kinds characteristic of StyleGAN networks

Implementation of Hire-MLP: Vision MLP via Hierarchical Rearrangement and An Image Patch is a Wave: Phase-Aware Vision MLP.

CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation

Unofficial Implementation of MLP-Mixer, gMLP, resMLP, Vision Permutator, S2MLPv2, RaftMLP, ConvMLP, ConvMixer in Jittor and PyTorch.

PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

3D detection and tracking viewer (visualization) for kitti & waymo dataset

Implementation of parameterized soft-exponential activation function.

Automatically creates genre collections for your Plex media

Contra is a lightweight, production ready Tensorflow alternative for solving time series prediction challenges with AI

A collection of Google research projects related to Federated Learning and Federated Analytics.

Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

Code of paper: "DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks"

Repository for "Exploring Sparsity in Image Super-Resolution for Efficient Inference", CVPR 2021

[ICCV 2021 Oral] SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer

Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder