SOURCE-LINKED INTELLIGENCE

Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Object-Centric Learning (OCL) aims to decompose images into objects without human annotations. A major family of mainstream methods uses Slot Attention to aggregate image features into object-level representations and then from them reconstructs masked image content, i.e., Random Masking (RM), to provide self-supervision. The recent method DIAS simply masks image patches at uniform randomness yet achieves competitive object discovery accuracy. Since attention during aggregation already possesses object discovery ability, we explore using it to develop a better image patch masking strategy, i.e

Read original source ↗ Open in workspace

recordType

paper

region

Global