This is an official implementation of semantic segmentation for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

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

Understanding Convolution for Semantic Segmentation

Papers and Benchmarks about semantic segmentation, instance segmentation, panoptic segmentation and video segmentation

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

Add bisenetv2. My implementation of BiSeNet

Code for https://arxiv.org/abs/1611.10080

[ICLR 2020] "FasterSeg: Searching for Faster Real-time Semantic Segmentation" by Wuyang Chen, Xinyu Gong, Xianming Liu, Qian Zhang, Yuan Li, Zhangyang Wang

Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)

[ICCV19] AdaptIS: Adaptive Instance Selection Network, https://arxiv.org/abs/1909.07829

This repository contains the source code of our work on designing efficient CNNs for computer vision

LightNet++: Boosted Light-weighted Networks for Real-time Semantic Segmentation

CGNet: A Light-weight Context Guided Network for Semantic Segmentation [arXiv preprint arXiv:1811.08201]

Code, data and benchmark from the paper "Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming" (NeurIPS 2019 ML4AD)

Code for Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells, CVPR '19

DeepLabv3, DeepLabv3+ and pretrained weights on VOC & Cityscapes

mIOU=80.02 on cityscapes. My implementation of deeplabv3+ (also know as 'Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation' based on the dataset of cityscapes).

Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation (BMVC2019)

Fully Convolutional HarDNet for Segmentation in Pytorch

IJCAI2020 🌇 Unsupervised Scene Adaptation with Memory Regularization in vivo

Semantic segmentation task for ADE20k & cityscapse dataset, based on several models.

PSPNet in Chainer

Criss-Cross Attention for Semantic Segmentation in pure Pytorch with a faster and more precise implementation.

Photographic Image Synthesis with Cascaded Refinement Networks - Pytorch Implementation

Switchable Normalization for semantic image segmentation and scene parsing.

A TensorFlow implementation of FCN-8s

ICNet implemented by pytorch, for real-time semantic segmentation on high-resolution images, mIOU=71.0 on cityscapes, single inference time is 19ms, FPS is 52.6.