In this paper, we present a Nuisance-label Supervision (NLS) module, which can make models more robust to nuisance factor variations. Nuisance factors are those irrelevant to a task, and an ideal model should be invariant to them. For example, an activity recognition model should perform consistently regardless of the change of clothes and background. But our experiments show existing models are far from this capability. So we explicitly supervise a model with nuisance labels to make extracted features less dependent on nuisance factors. Although the values of nuisance factors are rarely annotated, we demonstrate that besides existing annotations, nuisance labels can be acquired freely from data augmentation and synthetic data. Experiments show consistent improvement in robustness towards image corruption and appearance change in action recognition.
翻译:在本文中,我们提出了一个“骚扰标签监督”模块,该模块可以使模型对骚扰因素的变异性更具活力。骚扰因素与一项任务无关,理想模型应当对之无所适从。例如,活动识别模式应当始终如一地运行,而不论衣着和背景的变化。但我们的实验显示现有的模型远非这种能力。因此我们明确监督带有骚扰标签的模型,以使提取的特征不依赖于骚扰因素。尽管骚扰因素的价值很少附加说明,但我们证明,除了现有的说明外,从数据增强和合成数据中可以自由获取骚扰标签。实验显示,对形象腐败的稳健性和行动识别的外观变化在持续改善。