RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

The official homepage of the (outdated) COCO-Stuff 10K dataset.

The repository contains source code and models to use PixelNet architecture used for various pixel-level tasks. More details can be accessed at <http://www.cs.cmu.edu/~aayushb/pixelNet/>.

train test labels for sunrgbd

WB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].

CVPR2018 - pixel embedding & grouping for structured prediction, e.g., instance segmentation

[TIP] Deep Label Distribution Learning with Label Ambiguity

Pixel Attentional Gating for Parsimonious Per-Pixel Labeling

Semantic Understanding of Foggy Scenes with Purely Synthetic Data

Dataset and Evaluation Scripts for Obstacle Detection via Semantic Segmentation in a Marine Environment

CVPR2018 - scene parsing network regulated by geometric prior

Domain Adaptation for Semantic Segmentation at Nighttime

[CVPR-2018] Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation

DeepLabv3+ inference and training in MATLAB for Semantic Segmentation

Semantic segmentation and transfer learning using pretrained SalsaNext model in MATLAB

Semantic neural network to realize pixel-wise classification of 2D nano-material using Matlab

Some notes from various research papers

This example shows how to train a semantic segmentation network using deep learning.

ICIP 2019 paper