Caltech Fish Counting – Domain Adaptive Object Detection
CFC-DAOD is a domain adaptation extension to the Caltech Fish Counting domain generalization benchmark.
The goal is cross-domain object detection of a single class, "fish", in sonar videos. The source domain consists of data from one river, Kenai, and the target domain consists of data from another out-of-domain river, Channel. CFC-DAOD introduces new data from the target domain to be used for unsupervised domain adaptive object detection: 168k bounding box annotations in 29k frames sampled from 150 new videos captured over two days from 3 different sensors on the Channel river.
Variants: CFC-DAOD
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| Unsupervised Domain Adaptation | ALDI++ (ResNet50-FPN) | Align and Distill: Unifying and … | 2024-03-18 |
| Unsupervised Domain Adaptation | MIC (ResNet50-FPN) | Align and Distill: Unifying and … | 2024-03-18 |
| Unsupervised Domain Adaptation | AT (ResNet50-FPN) | Align and Distill: Unifying and … | 2024-03-18 |
| Unsupervised Domain Adaptation | PT (ResNet50-FPN) | Align and Distill: Unifying and … | 2024-03-18 |
| Unsupervised Domain Adaptation | UMT (ResNet50-FPN) | Align and Distill: Unifying and … | 2024-03-18 |
| Unsupervised Domain Adaptation | SADA (ResNet50-FPN) | Align and Distill: Unifying and … | 2024-03-18 |
Recent papers with results on this dataset: