A publicly available Nighttime Image Segmentation (NISeg) dataset
This repository contains 1000 low-light images and the hand-labeled salient objects as ground-truths
========================================================================
NISeg dataset contains 13 object categories, i.e., Cup: 1-91, Car: 92-122, Boat: 123-136, Dogs: 137-252, Building: 253-315, Stand: 316-365, Cat: 366-448, Bottle: 449-549, People: 550-681, Commodity: 682-881, Fruit: 882-933, Doll: 934-986, Chair: 987-1000
========================================================================
The complete dataset, including training and testing sets, can be download from Google Drive Link: https://drive.google.com/drive/folders/1H7pwWm9IHLjXzXZhCMjw4239MbQpx1rX?usp=sharing
========================================================================
If you find our dataset useful in your research, please consider citing our paper "Yu Zhang, Yiyue Hu, and Nan Mu, MBNet: Detecting Salient Object in Low-Light Scenes, IEEE International Conference on Systems, Man, and Cybernetics (SMC 2022)."
In case of any questions, please contact Nan Mu at nanmu@sicnu.edu.cn