Research output per year
Research output per year
Description
Common Objects Day and Night (CODaN) is an image classification dataset for zero-shot day-night domain adaptation / generalization.
The CODaN dataset consists of 15,500 224x224 colour images in 10 classes, with 1,550 images per class. There are 10,000 training images, 500 validation images, 2,500 daytime test images and 2,500 nighttime test images.
The dataset is collected from the excellent COCO, ImageNet and ExDark datasets. All images are filtered and cropped such that they have the same dimensions and are completely mutually exclusive, i.e. do not contain objects of different classes, nor do belong objects to multiple classes.
The CODaN dataset consists of 15,500 224x224 colour images in 10 classes, with 1,550 images per class. There are 10,000 training images, 500 validation images, 2,500 daytime test images and 2,500 nighttime test images.
The dataset is collected from the excellent COCO, ImageNet and ExDark datasets. All images are filtered and cropped such that they have the same dimensions and are completely mutually exclusive, i.e. do not contain objects of different classes, nor do belong objects to multiple classes.
| Date made available | 29 Nov 2023 |
|---|---|
| Publisher | TU Delft - 4TU.ResearchData |
| Date of data production | 2023 - |
-
On Color and Symmetries for Data Efficient Deep Learning
Lengyel, A., 2024, 143 p.Research output: Thesis › Dissertation (TU Delft)
Open AccessFile114 Downloads (Pure) -
Zero-Shot Day-Night Domain Adaptation with a Physics Prior
Lengyel, A., Garg, S., Milford, M. & van Gemert, J. C., 2021, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). O'Conner, L. (ed.). p. 4399 - 4409Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review
Open AccessFile