hansinahuja / semantic-segmentation

Implementing a fully convolutional network (FCN-8) for multi-class semantic segmentation.

Semantic-Segmentation

Performing multi-class semantic image segmentation using a fully convolutional network (FCN-8), a skip architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer. This model was proposed by Shelhamer, Long & Darrell in this research paper.

A few links

• Original research paper: Fully Convolutional Networks for Semantic Segmentation
• The dataset used is the sample data prepared by Divam Gupta. It can be found in ./dataset or here.
• Pretrained VGG16 weights can be downloaded using Keras. They have been stored in ./pretrained_weights as well.

Note: to use ./src/predict.py, first follow the instructions given in ./checkpoints/instructions.md.

Description

The detailed explanation of the model can be found in the aforementioned paper. The model described in the paper:

Visualization of model returned by ./src/create_model.py:

Result visualisation

Model tested on data in ./dataset/test/. An accuracy of 86.76% was obtained. Some of the results are as follows: