Trajectory Regularization Enhances Self-Supervised Geometric Representation

arXiv:2403.14973v1 Announce Type: cross
Abstract: Self-supervised learning (SSL) has proven effective in learning high-quality representations for various downstream tasks, with a primary focus on semantic tasks. However, its application in geometric tasks remains underexplored, partially due to the absence of a standardized evaluation method for geometric representations. To address this gap, we introduce a new pose-estimation benchmark for assessing SSL geometric representations, which demands training without semantic or pose labels and achieving proficiency in both semantic and geometric downstream tasks. …

abstract application arxiv cs.cv cs.lg evaluation focus gap however quality regularization representation self-supervised learning semantic ssl supervised learning tasks trajectory type