Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC -- Domain Incremental through Statistical Correction -- a simple online zero-forgetting approach which can incrementally learn new tasks (i.e weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow.
翻译:尽管深心神经网络为自主驾驶提供了令人印象深刻的视觉感知性表现,但它们对于不同天气条件的强健性仍需要关注。当将这些模型适应变化的环境时,例如不同的天气条件,它们往往会忘记以前学到的信息。这种灾难性的遗忘通常通过渐进式学习方法来解决,通常通过保留一个培训样本的记忆库或保存每个情景的整个模型或模型参数的副本来重新培训模型。虽然这些方法显示了令人印象深刻的结果,但它们可能容易出现可缩放问题,而且在所有天气条件下,它们都适用自主驾驶。在本文中,我们建议DISC -- -- 统计校正(Domain Encial Reclution) -- -- 一种简单的在线零缓冲方法,可以逐步学习新任务(即天气条件),而无需再培训或花费昂贵的记忆库。我们为每项任务储存的唯一信息是统计参数,因为我们根据第一和第二顺序统计的变化对每个领域进行了分类。因此,在每次任务到来时,我们只是“插入和播放”统计矢量矢量,用于模型中的相应任务,并且它立即开始很好地完成这项任务。我们展示了方法的效能,通过测试它是如何在高空的天气中,我们测试它是如何探索的轨道上如何探索。