Spatial-then-Temporal Self-Supervised Learning for Video Correspondence
share
Learning temporal correspondence from unlabeled videos is of vital importance in computer vision, and has been tackled by different kinds of self-supervised pretext tasks. For the self-supervised learning, recent studies suggest using large-scale video datasets despite the training cost. We propose a spatial-then-temporal pretext task to address the training data cost problem. The task consists of two steps. First, we use contrastive learning from unlabeled still image data to obtain appearance-sensitive features. Then we switch to unlabeled video data and learn motion-sensitive features by reconstructing frames. In the second step, we propose a global correlation distillation loss to retain the appearance sensitivity learned in the first step, as well as a local correlation distillation loss in a pyramid structure to combat temporal discontinuity. Experimental results demonstrate that our method surpasses the state-of-the-art self-supervised methods on a series of correspondence-based tasks. The conducted ablation studies verify the effectiveness of the proposed two-step task and loss functions.
READ FULL TEXT