Action Units (AU) are muscular activations used to describe facial expressions. Therefore accurate AU recognition unlocks unbiaised face representation which can improve face-based affective computing applications. From a learning standpoint AU detection is a multi-task problem with strong inter-task dependencies. To solve such problem, most approaches either rely on weight sharing, or add explicit dependency modelling by decomposing the joint task distribution using Bayes chain rule. If the latter strategy yields comprehensive inter-task relationships modelling, it requires imposing an arbitrary order into an unordered task set. Crucially, this ordering choice has been identified as a source of performance variations. In this paper, we present Multi-Order Network (MONET), a multi-task method with joint task order optimization. MONET uses a differentiable order selection to jointly learn task-wise modules with their optimal chaining order. Furthermore, we introduce warmup and order dropout to enhance order selection by encouraging order exploration. Experimentally, we first demonstrate MONET capacity to retrieve the optimal order in a toy environment. Second, we validate MONET architecture by showing that MONET outperforms existing multi-task baselines on multiple attribute detection problems chosen for their wide range of dependency settings. More importantly, we demonstrate that MONET significantly extends state-of-the-art performance in AU detection.

翻译：动作单元（AU）是用于描述面部表情的肌肉激活模式。因此，准确的AU识别能够揭示无偏见的面部表征，从而改进基于面部的情感计算应用。从学习角度看，AU检测是一个具有强任务间依赖性的多任务问题。为解决此类问题，大多数方法要么依赖权重共享，要么通过贝叶斯链式法则分解联合任务分布来添加显式依赖建模。尽管后一种策略能实现全面的任务间关系建模，但它需要为无序的任务集强加任意顺序。关键在于，这种顺序选择已被确定为导致性能差异的来源。本文提出多阶网络（MONET），一种具有联合任务顺序优化的多任务方法。MONET通过可微分的顺序选择机制，联合学习任务模块及其最优链接顺序。此外，我们引入预热训练与顺序丢弃机制，通过鼓励顺序探索来增强顺序选择。实验部分，我们首先在模拟环境中验证了MONET检索最优顺序的能力。其次，通过选择具有广泛依赖设置的多个属性检测问题，证明MONET架构优于现有多任务基线方法。更重要的是，我们证明了MONET在AU检测任务中显著扩展了当前最优性能。