Abstract: Self-training is a novel learning paradigm that generates pseudolabels for unlabeled data, enabling deep learning models to be trained without the need for humanlabeled data. This article ...
Abstract: Real-time semantic segmentation plays an important role in auto vehicles. However, most real-time small object segmentation methods fail to obtain satisfactory performance on small objects, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results