AI RESEARCH
Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning
arXiv CS.LG
•
ArXi:2603.22758v1 Announce Type: cross Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but existing slot-attention models often suffer from severe over-fragmentation. This is because the model is implicitly encouraged to occupy all slots to minimize the reconstruction objective, thereby representing a single object with multiple redundant slots. We tackle this limitation with a reconstruction-guided slot curriculum (SlotCurri)