Multi Positive Contrastive Learning with Pose-Consistent Generated Images

arXiv:2404.03256v1 Announce Type: new
Abstract: Model pre-training has become essential in various recognition tasks. Meanwhile, with the remarkable advancements in image generation models, pre-training methods utilizing generated images have also emerged given their ability to produce unlimited training data. However, while existing methods utilizing generated images excel in classification, they fall short in more practical tasks, such as human pose estimation. In this paper, we have experimentally demonstrated it and propose the generation of visually distinct images with identical human …

abstract arxiv become classification consistent cs.cv data excel generated however image image generation image generation models images positive pre-training recognition tasks training training data type