# TinyBenchmark **Repository Path**: pluto1314/TinyBenchmark ## Basic Information - **Project Name**: TinyBenchmark - **Description**: No description available - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 1 - **Forks**: 0 - **Created**: 2020-05-30 - **Last Updated**: 2021-09-20 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README # Scale Match for Tiny Person Detection ------------------------ [[paper]](http://openaccess.thecvf.com/content_WACV_2020/papers/Yu_Scale_Match_for_Tiny_Person_Detection_WACV_2020_paper.pdf) [[ECCVW]](https://rlq-tod.github.io/challenge1.html) [[challenge]](https://competitions.codalab.org/competitions/24551) ## TODO list 1. add a tutorial that how to train on TinyPerson with scale match on COCO 2. add a tutorial that how to train on other dataset 3. add a tutorial that how to train a strong baseline for competetion ## TinyPerson Dataset The dataset will be used to for ECCV2020 workshop [RLQ-TOD'20 @ ECCV](https://rlq-tod.github.io/challenge1.html), [TOD challenge](https://competitions.codalab.org/competitions/24551) #### Download link: [Official Site](http://vision.ucas.ac.cn/resource.asp): recomended, download may faster
[Baidu Pan](https://pan.baidu.com/s/1kkugS6y2vT4IrmEV_2wtmQ) password: pmcq
[Google Driver](https://drive.google.com/open?id=1KrH9uEC9q4RdKJz-k34Q6v5hRewU5HOw)
For more details about TinyPerson dataset, please see [Dataset](dataset/). ![](figure/annotation_rule.jpg) ## Tiny Benchmark The benchmark is based on [maskrcnn_benchmark](https://github.com/facebookresearch/maskrcnn-benchmark) and [citypersons code](https://bitbucket.org/shanshanzhang/citypersons/src/default/evaluation/). For more details about the benchmark, please see [Tiny Benchmark](tiny_benchmark/). ## Scale Match ![](figure/scale_match.jpg) ## Citation If you use the code and benchmark in your research, please cite: ``` @inproceedings{yu2020scale, title={Scale Match for Tiny Person Detection}, author={Yu, Xuehui and Gong, Yuqi and Jiang, Nan and Ye, Qixiang and Han, Zhenjun}, booktitle={The IEEE Winter Conference on Applications of Computer Vision}, pages={1257--1265}, year={2020} } ```