AI RESEARCH
Smoothing Slot Attention Iterations and Recurrences
arXiv CS.CV
•
ArXi:2508.05417v3 Announce Type: replace Slot Attention (SA) lies at the heart of mainstream Object-Centric Learning (OCL). Image features can be aggregated into object-level representations by SA iteratively refining cold-start query slots. For video, such aggregation proceeds by SA recurrently shared across frames, with queries cold-started on the first frame while transitioned from the previous frame's slots thereafter.