OBJ-MDA
Introduced by Pasqualino et al. in A Multi Camera Unsupervised Domain Adaptation Pipeline for Object Detection in Cultural Sites through Adversarial Learning and Self-Training
The dataset contains images of 16 artworks included in the cultural site “Galleria Regionale di Palazzo Bellomo2”. The collection covers different types of artworks, as well as books, sculptures and paintings. The dataset three domains: i) synthetic images generated from a 3D model of the cultural site and automatically labeled during the generation process; ii) real images collected by 10 visitors with a HoloLens device and manually labeled; iii) realimages collected by the same visitors with a GoPro and manually labeled.
Benchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
OBJ-MDA
|
STMDA-RetinaNet
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
