论文标题
MTI-NET：多任务学习的多尺度任务交互网络
MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learning
论文作者
论文摘要
在本文中，我们争论在多任务学习设置中提炼任务信息时，考虑任务交互的重要性。与普遍的信念相反，我们表明，在一定尺度上具有高亲和力的任务不能保证在其他尺度上保留这种行为，反之亦然。我们提出了一种新颖的建筑，即MTI-NET，它以三种方式建立在这一发现的基础上。首先，它通过多尺度的多模式蒸馏单元在每个尺度上明确对任务交互进行建模。其次，它通过特征传播模块传播从下部到更高尺度的蒸馏任务信息。第三，它通过特征聚合单元从所有量表中汇总了精致的任务特征，以产生最终的每个任务预测。 在两个多任务密集标签数据集上进行的广泛实验表明，与先前的工作不同，我们的多任务模型可提供多任务学习的全部潜力，即，记忆足迹较小，计算数量减少和更好的性能W.R.T.单任务学习。该代码公开可用：https：//github.com/simonvandenhende/multi-task-learning-pytorch。
In this paper, we argue about the importance of considering task interactions at multiple scales when distilling task information in a multi-task learning setup. In contrast to common belief, we show that tasks with high affinity at a certain scale are not guaranteed to retain this behaviour at other scales, and vice versa. We propose a novel architecture, namely MTI-Net, that builds upon this finding in three ways. First, it explicitly models task interactions at every scale via a multi-scale multi-modal distillation unit. Second, it propagates distilled task information from lower to higher scales via a feature propagation module. Third, it aggregates the refined task features from all scales via a feature aggregation unit to produce the final per-task predictions. Extensive experiments on two multi-task dense labeling datasets show that, unlike prior work, our multi-task model delivers on the full potential of multi-task learning, that is, smaller memory footprint, reduced number of calculations, and better performance w.r.t. single-task learning. The code is made publicly available: https://github.com/SimonVandenhende/Multi-Task-Learning-PyTorch.
