We present a novel framework for contrastive learning of pixel-level representation using only unlabeled video. Without the need of ground-truth annotation, our method is capable of collecting well-defined positive correspondences by measuring their confidences and well-defined negative ones by appropriately adjusting their hardness during training. This allows us to suppress the adverse impact of ambiguous matches and prevent a trivial solution from being yielded by too hard or too easy negative samples. To accomplish this, we incorporate three different criteria that ranges from a pixel-level matching confidence to a video-level one into a bottom-up pipeline, and plan a curriculum that is aware of current representation power for the adaptive hardness of negative samples during training. With the proposed method, state-of-the-art performance is attained over the latest approaches on several video label propagation tasks.
|Title of host publication||Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021|
|Publisher||IEEE Computer Society|
|Number of pages||11|
|State||Published - 2021|
|Event||2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 - Virtual, Online, United States|
Duration: 19 Jun 2021 → 25 Jun 2021
|Name||Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition|
|Conference||2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021|
|Period||19/06/21 → 25/06/21|
Bibliographical noteFunding Information:
Acknowledgements : This work was supported by IITP grant funded by the Korea government (MSIT) (No.2020-0-00056, To create AI systems that act appropriately and effectively in novel situations that occur in open worlds) and the Yonsei University Research Fund of 2021 (2021-22-0001).
© 2021 IEEE