TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral
Alternatives To Tood
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
3 months agon,ullotherC
YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Cvpr2023 Papers With Code12,014
3 days ago10
CVPR 2023 论文和开源项目合集
Cvpr2023 Paper Code Interpretation11,480
2 months ago40
cvpr2022/cvpr2021/cvpr2020/cvpr2019/cvpr2018/cvpr2017 论文/代码/解读/直播合集,极市团队整理
7 hours ago2September 08, 2022492mitTypeScript
Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.
Computervision Recipes8,950
4 months ago65mitJupyter Notebook
Best Practices, code samples, and documentation for Computer Vision.
Pytorch Grad Cam7,414113 days ago25May 20, 202271mitPython
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
a day ago80mitC#
Experience, Learn and Code the latest breakthrough innovations with Microsoft AI
Awesome Object Detection6,707
a year ago6
Awesome Object Detection based on handong1587 github:
Jetson Inference6,428
2 days ago212mitC++
Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
9 hours ago232apache-2.0Python
AutoGluon: AutoML for Image, Text, Time Series, and Tabular Data
Alternatives To Tood
Select To Compare

Alternative Project Comparisons

TOOD: Task-aligned One-stage Object Detection (ICCV 2021 Oral)

Paper     Website


  • 【2023/01】 YOLOv8 adopts the Task Alignment Learning (TAL) of TOOD!
  • 【2022/09】 YOLOv6 adopts the Task Alignment Learning (TAL) of TOOD!
  • 【2022/03】 PP-YOLOE adopts the Task Alignment Learning (TAL) and an efficient version of the Task-aligned Head (T-Head)!


One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of spatial misalignment in predictions between the two tasks. In this work, we propose a Task-aligned One-stage Object Detection (TOOD) that explicitly aligns the two tasks in a learning-based manner. First, we design a novel Task-aligned Head (T-Head) which offers a better balance between learning task-interactive and task-specific features, as well as a greater flexibility to learn the alignment via a task-aligned predictor. Second, we propose Task Alignment Learning (TAL) to explicitly pull closer (or even unify) the optimal anchors for the two tasks during training via a designed sample assignment scheme and a task-aligned loss. Extensive experiments are conducted on MS-COCO, where TOOD achieves a 51.1 AP at single-model single-scale testing. This surpasses the recent one-stage detectors by a large margin, such as ATSS (47.7 AP), GFL (48.2 AP), and PAA (49.0 AP), with fewer parameters and FLOPs. Qualitative results also demonstrate the effectiveness of TOOD for better aligning the tasks of object classification and localization.

Method overview

Parallel head vs. T-head

method overview


  • MMDetection version 2.14.0.

  • Please see for installation and the basic usage of MMDetection.


# assume that you are under the root directory of this project,
# and you have activated your virtual environment if needed.
# and with COCO dataset in 'data/coco/'.

./tools/ configs/tood/ 4


./tools/ configs/tood/ work_dirs/tood_r50_fpn_1x_coco/epoch_12.pth 4 --eval bbox


For your convenience, we provide the following trained models (TOOD). All models are trained with 16 images in a mini-batch.

Model Anchor MS train DCN Lr schd AP (minival) AP (test-dev) Config Download
TOOD_R_50_FPN_1x Anchor-free No No 1x 42.5 42.7 config google / baidu
TOOD_R_50_FPN_anchor_based_1x Anchor-based No No 1x 42.4 42.8 config google / baidu
TOOD_R_101_FPN_2x Anchor-free Yes No 2x 46.2 46.7 config google / baidu
TOOD_X_101_FPN_2x Anchor-free Yes No 2x 47.6 48.5 config google / baidu
TOOD_R_101_dcnv2_FPN_2x Anchor-free Yes Yes 2x 49.2 49.6 config google / baidu
TOOD_X_101_dcnv2_FPN_2x Anchor-free Yes Yes 2x 50.5 51.1 config google / baidu

[0] All results are obtained with a single model and without any test time data augmentation such as multi-scale, flipping and etc..
[1] dcnv2 denotes deformable convolutional networks v2.
[2] Refer to more details in config files in config/tood/.
[3] Extraction code of baidu netdisk: tood.


Thanks MMDetection team for the wonderful open source project!


If you find TOOD useful in your research, please consider citing:

    title={TOOD: Task-aligned One-stage Object Detection},
    author={Feng, Chengjian and Zhong, Yujie and Gao, Yu and Scott, Matthew R and Huang, Weilin},
Popular Object Detection Projects
Popular Computer Vision Projects
Popular Artificial Intelligence Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Computer Vision
Object Detection