Mask What Matters: Saliency-Guided Video Self-Supervised Learning for Autonomous Driving

arXiv:2608.17178v1 Announce Type: new Abstract: Video self-supervised learning through masked spatiotemporal prediction has emerged as a promising paradigm for learning feature representations from unlabeled data. However, existing methods typically rely on random masking, which indiscriminately removes regions irrespective of their semantic or temporal relevance. In ego-centric driving videos, this can weaken the pretext signal since safety-critical cues such as pedestrians, vehicles, lane boun...