Code Monkey home page Code Monkey logo

cityscapes-segmentation's Introduction

Semantic Segmentation on Cityscapes Dataset

In an era of various devices rapidly getting dependent on the vision systems to see and interpret the world around them, detection and segmentation techniques have played an indispensable role by teaching these devices on how to decipher the world around them. In this project, we have implemented Recurrent Residual Neural Network based on U-Net model (R2-Unet) proposed by Alom et. al. for semantic segmentation on Cityscapes dataset. In addition to that we have proposed four different modifications to the R2U-Net architecture and compared their relative performances. Finally, the best modification of increasing model depth shows an improved detection of classes that were less frequently observed in the dataset.

The below image shows the comparison of model output between R2UNET and modified R2UNET on unseen images. First row shows the original images. Second row shows the predicted segmentation labels of R2U-Net model. Third row shows the predicted segmentation labels of modified R2U-Net.

image

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.