Exclusively Dark Image Dataset
The Exclusively Dark (ExDARK) dataset is a collection of 7,363 low-light images from very low-light environments to twilight (i.e 10 different conditions) with 12 object classes (similar to PASCAL VOC) annotated on both image class level and local object bounding boxes.
Source: https://github.com/cs-chan/Exclusively-Dark-Image-Dataset
Variants: ExDark
This dataset is used in 2 benchmarks:
| Task | Model | Paper | Date |
|---|---|---|---|
| 2D Object Detection | WARLearn | WARLearn: Weather-Adaptive Representation Learning | 2024-11-21 |
| 2D Object Detection | MAET | Multitask AET with Orthogonal Tangent … | 2022-05-06 |
Recent papers with results on this dataset: