The smallNORB dataset is a datset for 3D object recognition from shape. It contains images of 50 toys belonging to 5 generic categories: four-legged animals, human figures, airplanes, trucks, and cars. The objects were imaged by two cameras under 6 lighting conditions, 9 elevations (30 to 70 degrees every 5 degrees), and 18 azimuths (0 to 340 every 20 degrees).
The training set is composed of 5 instances of each category (instances 4, 6, 7, 8 and 9), and the test set of the remaining 5 instances (instances 0, 1, 2, 3, and 5).
Source: https://cs.nyu.edu/~ylclab/data/norb-v1.0-small/
Image Source: https://www.kaggle.com/nepuerto/the-small-norb-dataset-v10
Variants: smallNORB
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Image Classification | Efficient-CapsNet | Efficient-CapsNet: Capsule Network with Self-Attention … | 2021-01-29 |
| Image Classification | Heinsen Routing | An Algorithm for Routing Capsules … | 2019-11-02 |
| Image Classification | VB-Routing | Capsule Routing via Variational Bayes | 2019-05-27 |
| Image Classification | FRMS | Fast Dynamic Routing Based on … | 2018-05-28 |
| Image Classification | DCNet | Dense and Diverse Capsule Networks: … | 2018-05-10 |
| Image Classification | CapsNet | Dynamic Routing Between Capsules | 2017-10-26 |
Recent papers with results on this dataset: