EventDance: Unsupervised Source-free Cross-modal Adaptation for Event-based Object Recognition

arXiv:2403.14082v1 Announce Type: new
Abstract: In this paper, we make the first attempt at achieving the cross-modal (i.e., image-to-events) adaptation for event-based object recognition without accessing any labeled source image data owning to privacy and commercial issues. Tackling this novel problem is non-trivial due to the novelty of event cameras and the distinct modality gap between images and events. In particular, as only the source model is available, a hurdle is how to extract the knowledge from the source model …

abstract arxiv cameras commercial cs.cv data event events free image image data modal novel object paper privacy recognition type unsupervised