RGBT-Tiny is a large-scale visible-thermal benchmark, which consists of 115 high-quality paired image sequences, 93K frames and 1.2M manual annotations, and covers abundant targets and diverse scenarios. Details of this dataset can be found in our paper. Over 81% of targets are smaller than 16x16, and we provide paired bounding box annotations with tracking ID to offer an extremely challenging benchmark with wide-range applications, such as RGBT fusion, detection, and tracking.
★ Baseline Models and codes will be released in June or July 2025.
SAFit results achieved by ATSS equipped with different losses in visible and thermal modalities of RGBT-Tiny dataset.
SAFit and IoU results achieved by ATSS equipped with different losses in COCO dataset.
Table 1 SAFit-based results of existing visible detection (V-D), visible SOD (V-SOD), thermal SOD (T-SOD), visible-thermal detection methods (VT-D) methods on RGBT-Tiny dataset.
Table 2 IoU-based results of existing visible detection (V-D), visible SOD (V-SOD), thermal SOD (T-SOD), visible-thermal detection methods (VT-D) methods on RGBT-Tiny dataset.
To access RGBT-Tiny dataset, please fill the following form: [Google Forms], [Microsoft Forms]
@article{RGBT-Tiny,
title = {Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines},
author = {Xinyi Ying and Chao Xiao and Ruojing Li and Xu He and Boyang Li and Xu Cao and Zhaoxu Li and Yingqian Wang and Mingyuan Hu and Qingyu Xu and Zaiping Lin and Miao Li and Shilin Zhou and Wei An and Weidong Sheng and Li Liu},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)},
year = {2025},
}
MOT label for RGBT-Tiny is available at https://github.com/xuqingyu26/HGTMT
Please contact us at yingxinyi18@nudt.edu.cn for any questions.