awesome-multi-task-learning and Awesome-Multi-Task-Learning
These are competing curated lists of the same subject matter, with A offering broader coverage (datasets, codebases, and papers) while B focuses primarily on published research works.
About awesome-multi-task-learning
thuml/awesome-multi-task-learning
A curated list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.
This is a curated collection for machine learning practitioners and researchers interested in Multi-Task Learning (MTL). It brings together a wide array of resources, including datasets for computer vision, natural language processing, and recommendation systems, along with research papers and codebases. You can find examples of how to train models to perform several related tasks simultaneously, such as segmenting images, estimating depth, and detecting edges all at once.
About Awesome-Multi-Task-Learning
WeiHongLee/Awesome-Multi-Task-Learning
An up-to-date list of works on Multi-Task Learning
This resource helps machine learning researchers and practitioners understand the latest advancements in Multi-Task Learning (MTL). It provides a curated collection of research papers, surveys, benchmarks, and code implementations, allowing you to explore different approaches and their applications. You'll find materials covering various real-world tasks like urban scene understanding, object detection, and image classification, aiding in the development of more efficient and robust AI models.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work