Optical flows associated with our work "We're Not Using Videos Effectively: An Updated Domain Adaptive Video Segmentation Baseline" See the [github](https://github.com/SimarKareer/UnifiedVideoDA) for

Hugging Face2024-01-28 更新150

2021 Smoky Mountains Conference Data Challenge Synthetic-to-Real Domain Adaptation for Autonomous Driving Dataset

域适应

语义分割

The dataset is comprised of both real and synthetic images from a vehicleâs forward-facing camera. Each camera image is accompanied by a corresponding pixel-level semantic segmentation image (all fi

DataCite Commons2021-03-27 更新60

多源域适应文本识别数据集

文本识别

域适应

多源域适应文本识别数据集是由北京邮电大学创建的，包含超过520万张图像，分为五个不同的域：合成域、文档域、街景域、手写域和车牌域。该数据集是首个多域文本识别数据集，旨在解决文本识别中的域适应问题。数据集的创建过程涉及从多个来源收集和过滤图像，确保覆盖广泛的文本样式和背景。该数据集适用于深度学习模型在不同域间的适应性训练，特别是在解决字体多样性和复杂背景带来的挑战方面。

arXiv2021-08-25 更新250

Building Damage Detection based on Multi-source Adversarial Domain Adaptation

建筑物损坏检测

域适应

Hurricane dataset

DataCite Commons2021-02-04 更新100