Seg-Uncertainty
Scene Adaptation Framework
A deep learning framework for unsupervised scene adaptation with memory regularization and pseudo label learning via uncertainty estimation
IJCAI2020 & IJCV2021 Unsupervised Scene Adaptation with Memory Regularization in vivo
387 stars
13 watching
51 forks
Language: Python
last commit: about 1 year ago cityscapesdomain-adaptationdomainadaptationgta5ijcaiijcai2020ijcvmrnetpytorchpytorch-implementationrobotcarself-driving-carsemantic-segmentationsynthiatransfer-learning
Related projects:
Repository | Description | Stars |
---|---|---|
| A deep learning framework for real-time uncertainty-aware semantic segmentation of LiDAR point clouds for autonomous driving applications. | 419 |
| Provides tools and methods to quantify uncertainty in deep learning models and improve their reliability | 320 |
| Scripts to generate datasets for an image generation task using Generative Adversarial Networks and deep learning techniques | 37 |
| Software implementing probabilistic models for uncertainty estimation in data analysis | 91 |
| Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,336 |
| This project implements a deep learning-based approach to adapt semantic segmentation models from one domain to another. | 851 |
| A framework for unsupervised depth and ego-motion estimation from monocular videos using deep learning | 1,977 |
| A PyTorch implementation of a deep learning-based method for generating interactive scenes with specified object attributes and relations | 188 |
| Provides pre-trained and customizable semantic segmentation model in MATLAB | 23 |
| This project proposes a solution to predict salient areas in images using convolutional neural networks. | 186 |
| Provides pre-trained deep learning models for scene classification on the Places365 dataset | 1,935 |
| A PyTorch implementation of a deep learning model for learning room layouts from 360 photos and providing tools for layout analysis and data augmentation. | 325 |
| An open-source framework for adapting representation models to various tasks and industries | 1,743 |
| Reimplementation of a neural network model for conditional segmentation of ambiguous images | 548 |
| Generates synthetic seismic data with associated labels to train deep learning models | 58 |