Abstract: Source-free object detection (SFOD) transfers a source-trained model to a target domain using only unlabeled data. Most SFOD methods adopt a mean-teacher framework, filtering pseudo labels ...
Abstract: Few-shot object detection (FSOD) in remote sensing imagery aims to achieve accurate detection of novel object categories with limited training samples. However, current mainstream transfer ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results