Self-Supervised Multi-Object Tracking with Path Consistency

arXiv:2404.05136v1 Announce Type: new
Abstract: In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision. Our key idea is that, to track a object through frames, we can obtain multiple different association results from a model by varying the frames it can observe, i.e., skipping frames in observation. As the differences in observations do not alter the identities of objects, the obtained association results should be consistent. Based …

abstract arxiv association concept cs.ai cs.cv identity key learn multiple novel object paper path results robust supervision through tracking type