Wild-Time
Distribution shift benchmark
A benchmark of in-the-wild distribution shifts over time for evaluating machine learning models
Benchmark for Natural Temporal Distribution Shift (NeurIPS 2022)
61 stars
2 watching
8 forks
Language: Python
last commit: over 1 year ago Related projects:
| Repository | Description | Stars |
|---|---|---|
 pku-yuangroup/chronomagic-bench | A benchmark and dataset for evaluating text-to-video generation models' ability to generate coherent and varied metamorphic time-lapse videos. | 186 |
 minzhang-whu/change-detection-review | A comprehensive review of change detection methods using artificial intelligence and various machine learning frameworks. | 837 |
 felixgithub2017/mmcu | Evaluates the semantic understanding capabilities of large Chinese language models using a multimodal dataset. | 87 |
 yanhengwang-heu/ieee_tgrs_sstformer | A toolbox implementing deep learning-based change detection for hyperspectral images using spectral, spatial, and temporal transformations. | 27 |
 hszhao/semseg | A PyTorch implementation of semantic segmentation models with support for multiprocessing training and various backbones. | 1,343 |
 hfawaz/dl-4-tsc | This project provides a framework for evaluating and comparing different deep learning architectures for time series classification tasks. | 1,558 |
 x-datainitiative/tick | A Python module for statistical learning with an emphasis on time-dependent modeling, providing tools for machine learning, point-process modeling, and optimization. | 491 |
 rjt1990/pyflux | A comprehensive time series modeling library with various statistical models and inference methods. | 2,111 |
 xjtushujun/meta-weight-net | An implementation of a meta-learning algorithm to improve sample weighting in classification tasks with noisy labels. | 281 |
 wenkehuang/rethinkfl | Improves federated learning performance by incorporating domain knowledge and regularization to adapt models across diverse domains | 91 |
 amazon-science/tgl | A framework for training temporal graphs on large datasets | 192 |
 nixtla/mlforecast | A Python library for scalable machine learning-based time series forecasting with efficient feature engineering and out-of-the-box compatibility. | 899 |
 catboost/benchmarks | Comparative benchmarks of various machine learning algorithms | 169 |
 tianyi-lab/hallusionbench | An image-context reasoning benchmark designed to challenge large vision-language models and help improve their accuracy | 243 |
 jpeg729/pytorch_bits | An experimental framework for developing and testing deep learning models on time-series prediction tasks | 79 |