Adapting Object Detectors via Selective Cross-Domain Alignment

CVPR, pp. 687-696, 2019.

Cited by: 43|Views152
EI
Weibo:
We have proposed a region-level adaptation framework for object detection

Abstract:

State-of-the-art object detectors are usually trained on public datasets. They often face substantial difficulties when applied to a different domain, where the imaging condition differs significantly and the corresponding annotated data are unavailable (or expensive to acquire). A natural remedy is to adapt the model by aligning the imag...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments