Don't ignore Dropout in Fully Convolutional Networks

TL;DR

This paper demonstrates that applying appropriate Dropout techniques, including scheduling and SpatialDropout, can significantly improve the performance of DeepLabv3+ in image segmentation tasks with limited data, even with Batch Normalization present.

Contribution

It shows that strategic Dropout application can enhance segmentation accuracy in low-data scenarios, challenging the notion that Batch Normalization diminishes Dropout effectiveness.

Findings

Dropout scheduling combined with SpatialDropout improves mIoU from 0.49 to 0.59.

Proper Dropout placement yields significant performance gains in small dataset training.

Dropout remains effective even with extensive Batch Normalization.

Abstract

Data for Image segmentation models can be costly to obtain due to the precision required by human annotators. We run a series of experiments showing the effect of different kinds of Dropout training on the DeepLabv3+ Image segmentation model when trained using a small dataset. We find that when appropriate forms of Dropout are applied in the right place in the model architecture that non-insignificant improvement in Mean Intersection over Union (mIoU) score can be observed. In our best case, we find that applying Dropout scheduling in conjunction with SpatialDropout improves baseline mIoU from 0.49 to 0.59. This result shows that even where a model architecture makes extensive use of Batch Normalization, Dropout can still be an effective way of improving performance in low data situations.