SegNet implementation & experiments in Chainer

Deeplab for semantic segmentation implemented by MXNet

Semantic segmentation for visual terrain classification and autonomous navigation in TensorFlow

KERAS: Multimodal Deep Learning for Semantic Segmentation (RGB, NIR Streams) - multiple architectures

Comparison of FCN and CNN on a semantic segmentation task.

An implementation of a fully convolutional network for road segmentation using vgg16 as the encoder network

Image Segmentation by Iterative Inference from Conditional Score Estimation

The semantic segmentation elective project for Udacity's self-driving car program

Semantic Segmentation of open road segments - Part of Udacity SDCND

Using a U-Net for image segmentation, blending predicted patches smoothly is a must to please the human eye.

Semantic Segmentation for Coral Reefs and Mangroves

Semantic Image Segmentation - using deep learning and computer vision to identify classes of objects in image. For Self Driving Cars.

Labeled the pixels of a road in images using a Fully Convolutional Network (FCN).

This Project is Semantic Segmentation Project of Term 3 of Udacity Self-Driving Car Engineer Nanodegree.

DeepLab-ResNet rebuilt in TensorFlow 1.1, updated to include CRF, weighted classes, and prediction-time augmentation

Image Semantic Segmentation using TensorFlow (for Kaggle Carvarna Challenge)

[Caffe] A deep convnet developed for semantic segmentation task.

Solution for the Carvana Image Masking Challenge on Kaggle. It uses a custom version of RefineNet with Squeeze-and-Excitation modules implemented in PyTorch. It was a part of the final ensemble that was ranked 23 out of 735 teams (top 4%).

A TensorFlow implementation of Fully Convolutional Networks (by http://fcn.berkeleyvision.org) which can be used for any segmentation dataset with any number of classes