This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks, a quality of meta learning. It is important to highlight that we focus on heterogeneous tasks, which are of distinct kind, in contrast to typically considered homogeneous tasks (e.g., if all tasks are classification or if all tasks are regression tasks). The fundamental idea is to train a multi-task model, such that when an unseen task is introduced, it can learn in fewer steps whilst offering a performance at least as good as conventional single task learning on the new task or inclusion within the MTL. By conducting various experiments, we demonstrate this paradigm on two datasets and four tasks: NYU-v2 and the taskonomy dataset for which we perform semantic segmentation, depth estimation, surface normal estimation, and edge detection. MTML achieves state-of-the-art results for three out of four tasks for the NYU-v2 dataset and two out of four for the taskonomy dataset. In the taskonomy dataset, it was discovered that many pseudo-labeled segmentation masks lacked classes that were expected to be present in the ground truth; however, our MTML approach was found to be effective in detecting these missing classes, delivering good qualitative results. While, quantitatively its performance was affected due to the presence of incorrect ground truth labels. The the source code for reproducibility can be found at https://github.com/ricupa/MTML-learn-how-to-adapt-to-unseen-tasks.

翻译：本文提出多任务元学习（MTML），融合了多任务学习（MTL）与元学习两种范式，旨在兼顾两者优势。具体而言，该方法聚焦于同时学习多个任务（MTL的核心要素）与快速适应新任务（元学习的关键特性）。需强调的是，我们关注的是异构任务（即不同类型的任务），而非通常考虑的同构任务（例如所有任务均为分类任务或回归任务）。其核心思想是训练一个多任务模型，使得当引入未见任务时，该模型能够以更少的步骤完成学习，同时在性能上至少不低于在新任务上单独采用传统单任务学习或将其纳入MTL框架的效果。通过开展多项实验，我们在两个数据集（NYU-v2与taskonomy）及四个任务（语义分割、深度估计、表面法线估计与边缘检测）上验证了这一范式。在NYU-v2数据集的四个任务中，MTML在其中三个任务上取得了最优结果；在taskonomy数据集的四个任务中，则有两个任务达到最优。在taskonomy数据集中，我们发现许多伪标注分割掩码缺失了本应存在于真实标注中的类别，但我们的MTML方法能有效检测这些缺失类别，并取得良好的定性结果。然而，由于错误真实标注的存在，其定量性能受到一定影响。可复现性研究的源代码见：https://github.com/ricupa/MTML-learn-how-to-adapt-to-unseen-tasks。