ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
The central idea of contrastive learning is to discriminate between different instances and force different views from the same instance to share the same representation. To avoid trivial solutions, augmentation plays an important role in generating different views, among which random cropping is shown to be effective for the model …