Contrastive Transformation for Self-supervised Correspondence Learning
Keywords:Unsupervised & Self-Supervised Learning
AbstractIn this paper, we focus on the self-supervised learning of visual correspondence using unlabeled videos in the wild. Our method simultaneously considers intra- and inter-video representation associations for reliable correspondence estimation. The intra-video learning transforms the image contents across frames within a single video via the frame pair-wise affinity. To obtain the discriminative representation for instance-level separation, we go beyond the intra-video analysis and construct the inter-video affinity to facilitate the contrastive transformation across different videos. By forcing the transformation consistency between intra- and inter-video levels, the fine-grained correspondence associations are well preserved and the instance-level feature discrimination is effectively reinforced. Our simple framework outperforms the recent self-supervised correspondence methods on a range of visual tasks including video object tracking (VOT), video object segmentation (VOS), pose keypoint tracking, etc. It is worth mentioning that our method also surpasses the fully-supervised affinity representation (e.g., ResNet) and performs competitively against the recent fully-supervised algorithms designed for the specific tasks (e.g., VOT and VOS).
How to Cite
Wang, N., Zhou, W., & Li, H. (2021). Contrastive Transformation for Self-supervised Correspondence Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 10174-10182. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17220
AAAI Technical Track on Machine Learning IV