The objective of this paper is self-supervised learning of spatio-temporal embeddings from video, suitable for human action recognition. We make three contributions: First, we introduce the Dense Predictive Coding (DPC) framework for self-supervised representation learning on videos. This learns a dense encoding of spatio-temporal blocks by recurrently predicting future representations; Second, we propose a curriculum training scheme to predict further into the future with progressively less temporal context. This encourages the model to only encode slowly varying spatial-temporal signals, therefore leading to semantic representations; Third, we evaluate the approach by first training the DPC model on the Kinetics-400 dataset with self-supervised learning, and then finetuning the representation on a downstream task, i.e. action recognition. With single stream~(RGB only), DPC pretrained representations achieve state-of-the-art self-supervised performance on both UCF101(75.7% top1 acc) and HMDB51(35.7% top1 acc), outperforming all previous learning methods by a significant margin, and approaching the performance of a baseline pre-trained on ImageNet.

2+
下载
关闭预览

相关内容

表示学习是通过利用训练数据来学习得到向量表示,这可以克服人工方法的局限性。 表示学习通常可分为两大类,无监督和有监督表示学习。大多数无监督表示学习方法利用自动编码器(如去噪自动编码器和稀疏自动编码器等)中的隐变量作为表示。 目前出现的变分自动编码器能够更好的容忍噪声和异常值。 然而,推断给定数据的潜在结构几乎是不可能的。 目前有一些近似推断的策略。 此外,一些无监督表示学习方法旨在近似某种特定的相似性度量。提出了一种无监督的相似性保持表示学习框架,该框架使用矩阵分解来保持成对的DTW相似性。 通过学习保持DTW的shaplets,即在转换后的空间中的欧式距离近似原始数据的真实DTW距离。有监督表示学习方法可以利用数据的标签信息,更好地捕获数据的语义结构。 孪生网络和三元组网络是目前两种比较流行的模型,它们的目标是最大化类别之间的距离并最小化了类别内部的距离。
Top