Anticipating future events is an essential feature for intelligent systems and embodied AI. However, compared to the traditional recognition task, the uncertainty of future and reasoning ability requirement make the anticipation task very challenging and far beyond solved. In this filed, previous methods usually care more about the model architecture design or but few attention has been put on how to train an anticipation model with a proper learning policy. To this end, in this work, we propose a novel training scheme called Dynamic Context Removal (DCR), which dynamically schedules the visibility of observed future in the learning procedure. It follows the human-like curriculum learning process, i.e., gradually removing the event context to increase the anticipation difficulty till satisfying the final anticipation target. Our learning scheme is plug-and-play and easy to integrate any reasoning model including transformer and LSTM, with advantages in both effectiveness and efficiency. In extensive experiments, the proposed method achieves state-of-the-art on four widely-used benchmarks. Our code and models are publicly released at https://github.com/AllenXuuu/DCR.
翻译:然而,与传统的认知任务相比,未来和推理能力要求的不确定性使得预期任务非常富有挑战性,而且远远无法解决。在此文件中,以往的方法通常更关心模型结构设计,或只是很少注意如何以适当的学习政策来培训预期模式。为此,我们提议了一个名为动态背景清除(DCR)的新式培训计划,在学习过程中动态环境清除(DCR),积极安排所观察到的未来在学习过程中的能见度。它遵循了类似人类的课程学习过程,即逐渐消除事件背景,以增加预期困难,直到达到最后的预期目标。我们的学习计划是插接和游戏,很容易整合任何推理模型,包括变异器和LSTM,在效力和效率方面都有优势。在广泛的实验中,拟议的方法在四种广泛使用的基准上达到了“最先进的”标准。我们的代码和模型在https://github.com/AllenXuuu/DCR公开发布。