pytorch-auto-drive

SOTA Re-identification Methods and Toolbox

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

Add bisenetv2. My implementation of BiSeNet

:couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:

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

[CVPR'22 & IJCV'24] Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels & Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation

Pytorch code for semantic segmentation using ERFNet

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

TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".