Semantic Segmentation of Remote Sensing Images

Objective: Develop an e!cient CNN architecture using Tensorflow for semantic segmentation of geospatial images into 4 classes

  1. Improved standard U-Net architecture by adding dilated & depthwise separable convolutions achieving a mean IoU of 0.73
  2. Employed unified focal loss in order to work with class imbalanced Landcover.AI dataset, along with custom dataloader pipeline