arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.07438cs.LGstat.ML
收藏

多任务元学习的注意特征重用

Attentive Feature Reuse for Multi Task Meta learning

University of Southern California(南加州大学)

Kiran Lekkala, Laurent Itti

摘要:

我们开发了用于同时学习多个任务的新算法(例如,图像分类,深度估计),以及用于适应那些高级任务内的不可见任务/域分布(例如,不同的环境)。首先,我们学习所有任务的共同表示。然后,我们提出了一个注意力机制动态专门的网络,在运行时,为每个任务。我们的方法是基于对骨干网络的每个特征图进行加权,基于其与特定任务的相关性。为了实现这一点,我们使注意力模块能够在训练过程中学习任务表示,这些任务表示用于获得注意力权重。我们的方法在新的、以前看不见的环境中提高了性能,并且比使用类似架构的标准现有元学习方法快1.5倍。我们强调了4个任务(图像分类,深度,消失点和表面法线估计)的多任务元学习的性能改进,每个任务超过10到25个测试域/环境,这是使用标准元学习技术(如MAML)无法实现的结果。

英文摘要:

We develop new algorithms for simultaneous learning of multiple tasks (e.g., image classification, depth estimation), and for adapting to unseen task/domain distributions within those high-level tasks (e.g., different environments). First, we learn common representations underlying all tasks. We then propose an attention mechanism to dynamically specialize the network, at runtime, for each task. Our approach is based on weighting each feature map of the backbone network, based on its relevance to a particular task. To achieve this, we enable the attention module to learn task representations during training, which are used to obtain attention weights. Our method improves performance on new, previously unseen environments, and is 1.5x faster than standard existing meta learning methods using similar architectures. We highlight performance improvements for Multi-Task Meta Learning of 4 tasks (image classification, depth, vanishing point, and surface normal estimation), each over 10 to 25 test domains/environments, a result that could not be achieved with standard meta learning techniques like MAML.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑