Displaying 1 to 20 from 27 results

semantic-segmentation-pytorch - Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset

  •    Python

This is a PyTorch implementation of semantic segmentation models on MIT ADE20K scene parsing dataset. This module differs from the built-in PyTorch BatchNorm as the mean and standard-deviation are reduced across all devices during training. The importance of synchronized batch normalization in object detection has been recently proved with a an extensive analysis in the paper MegDet: A Large Mini-Batch Object Detector, and we empirically find that it is also important for segmentation.

labelme - Image Polygonal Annotation with Python (polygon, rectangle, line, point and image-level flag annotation)

  •    Python

Labelme is a graphical image annotation tool inspired by http://labelme.csail.mit.edu. It is written in Python and uses Qt for its graphical interface. Fig 2. VOC dataset example of instance segmentation.

TuSimple-DUC - Understanding Convolution for Semantic Segmentation

  •    Python

by Panqu Wang, Pengfei Chen, Ye Yuan, Ding Liu, Zehua Huang, Xiaodi Hou, and Garrison Cottrell. This repository is for Understanding Convolution for Semantic Segmentation (WACV 2018), which achieved state-of-the-art result on the CityScapes, PASCAL VOC 2012, and Kitti Road benchmark.




crfasrnn_keras - CRF-RNN Keras/Tensorflow version

  •    Python

This repository contains Keras/Tensorflow code for the "CRF-RNN" semantic image segmentation method, published in the ICCV 2015 paper Conditional Random Fields as Recurrent Neural Networks. This paper was initially described in an arXiv tech report. The online demo of this project won the Best Demo Prize at ICCV 2015. Original Caffe-based code of this project can be found here. Results produced with this Keras/Tensorflow code are almost identical to that with the Caffe-based version. The root directory of the clone will be referred to as crfasrnn_keras hereafter.

piwise - Pixel-wise segmentation on VOC2012 dataset using pytorch.

  •    Python

Pixel-wise segmentation on the VOC2012 dataset using pytorch. For a more complete implementation of segmentation networks checkout semseg.

LightNet - LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

  •    Python

This repository contains the code (in PyTorch) for: "LightNet: Light-weight Networks for Semantic Image Segmentation " (underway) by Huijun Liu @ TU Braunschweig. Semantic Segmentation is a significant part of the modern autonomous driving system, as exact understanding the surrounding scene is very important for the navigation and driving decision of the self-driving car. Nowadays, deep fully convolutional networks (FCNs) have a very significant effect on semantic segmentation, but most of the relevant researchs have focused on improving segmentation accuracy rather than model computation efficiency. However, the autonomous driving system is often based on embedded devices, where computing and storage resources are relatively limited. In this paper we describe several light-weight networks based on MobileNetV2, ShuffleNet and Mixed-scale DenseNet for semantic image segmentation task, Additionally, we introduce GAN for data augmentation[17] (pix2pixHD) concurrent Spatial-Channel Sequeeze & Excitation (SCSE) and Receptive Field Block (RFB) to the proposed network. We measure our performance on Cityscapes pixel-level segmentation, and achieve up to 70.72% class mIoU and 88.27% cat. mIoU. We evaluate the trade-offs between mIoU, and number of operations measured by multiply-add (MAdd), as well as the number of parameters.


AdaptSegNet - Learning to Adapt Structured Output Space for Semantic Segmentation, CVPR 2018 (spotlight)

  •    Python

Pytorch implementation of our method for adapting semantic segmentation from the synthetic dataset (source domain) to the real dataset (target domain). Based on this implementation, our result is ranked 3rd in the VisDA Challenge. Learning to Adapt Structured Output Space for Semantic Segmentation Yi-Hsuan Tsai*, Wei-Chih Hung*, Samuel Schulter, Kihyuk Sohn, Ming-Hsuan Yang and Manmohan Chandraker IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 (spotlight) (* indicates equal contribution).

sunrgbd-meta-data - train test labels for sunrgbd

  •    Matlab

This alleviates the burden of having to install MATLAB (that requires a license) on your computer and parsing the .mat files in the SUN RGB-D dataset. To obtain the depth in meters, divide the png values by 10,000.

chainer-pspnet - PSPNet in Chainer

  •    Python

This is an unofficial implementation of Pyramid Scene Parsing Network (PSPNet) in Chainer. Caffe is NOT needed to convert .caffemodel to Chainer model. Use caffe_pb2.py.

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

  •    Python

One challenge of using a U-Net for image segmentation is to have smooth predictions, especially if the receptive field of the neural network is a small amount of pixels. For example, here is what the code in this repository can achieve, to make smooth predictions rather than jagged ones. For more information on the neural network architecture, check out this blog post on satellite image segmentation.

region-conv - Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade

  •    Cuda

This is the the authors' implementation of region convolution used in Deep Layer Cascade (LC). The use of this software is RESTRICTED to non-commercial research and educational purposes.

semantic-lane-detection - A robust lane detection system based on fully convolutional network for segmenting the road and the lane

  •    Jupyter

Description: use Fully Convolutional Network to segment road (drivable regions) and lane marks for self driving. The network was trained on the huge segmentation datasets for future maps provided by Mapillary. The testing videos are a random dashcam video on Youtube. The result for road segmentation is highly accurate but the result for lane mark segmentation is a lot less accurate. However, it is still good enough to estimate the rough positions of the lanes.

chainer-segnet - SegNet implementation & experiments in Chainer

  •    Python

This is an unofficial implementation of SegNet. This implementation doesn't use L-BFGS for optimization. This uses Adam with the default settings. This shell script performs download CamVid dataset from SegNet-Tutorial repository owned by the original auther of the SegNet paper.

kaggle-carvana - Solution for the Carvana Image Masking Challenge on Kaggle

  •    Python

The 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%). The goal of the Carvana Image Masking Challenge was to develop an algorithm that removes a background from a wide variety of car photos. Here you can see predictions from a trained neural network for 16 images of a single car.

cocostuff10k - The official homepage of the (outdated) COCO-Stuff 10K dataset.

  •    Matlab

The current release of COCO-Stuff-10K publishes both the training and test annotations and users report their performance individually. We invite users to report their results to us to complement this table. In the near future we will extend COCO-Stuff to all images in COCO and organize an official challenge where the test annotations will only be known to the organizers. For the updated table please click here.

superpixel-align - Official implementation of "Minimizing Supervision for Free-space Segmentation" paper

  •    Jupyter

This is the official implementation of "Minimizing Supervision for Free-space Segmentation ". BibTeX is here. The above shell script creates miniconda environment under this directory and install requirements below. The setup.sh installs all of them so you don't need to install the dependencies below by yourself.

tf-frrn - This repository contains code implementing the paper, Full Resolution Residual Networks for Semantic Segmentation in Street Scenes (FRRN) in Tensorflow

  •    Python

This repository contains code implementing the paper, Full Resolution Residual Networks for Semantic Segmentation in Street Scenes (FRRN) in Tensorflow. ⚠️ This is not an official implementation, and might have some glitch (,or a major defect).