Semantic Segmentation of buildings present in satellite images using encoder-decoder like convolutional neural networks is being achieved with relatively high pixel-wise metric scores. In this paper, we aim to exploit the power of fully convolutional neural networks for an instance segmentation task using extra added classes to the output along with the watershed processing technique to leverage better object-wise metric results. We also show that CutMix mixed data augmentations and the One-Cycle learning rate policy are greater regularization methods to achieve a better fit on the training data and increase performance. Furthermore, Mixed Precision Training provided more flexibility to experiment with bigger networks and batches while maintaining stability and convergence during training. We compare and show the effect of these additional changes throughout our whole pipeline to finally provide a set a tuned hyper-parameters that are proven to perform better.
翻译:在本文件中,我们的目标是利用完全进化神经网络的力量进行分解,例如利用产出增加的等级和流域处理技术进行分解。我们还表明,CutMix混合数据扩增和一循环学习率政策是更好的规范化方法,以更好地适应培训数据,提高性能。此外,混合精度培训提供了更大的灵活性,可以与更大的网络和分批进行实验,同时在培训期间保持稳定性和趋同。我们比较并展示了整个管道中这些额外变化的效果,以便最终提供一套经证明效果更好的调整的超参数。