Neural Slot Interpreters: Grounding Object Semantics in Emergent Slot Representations

arXiv:2403.07887v1 Announce Type: new
Abstract: Object-centric methods have seen significant progress in unsupervised decomposition of raw perception into rich object-like abstractions. However, limited ability to ground object semantics of the real world into the learned abstractions has hindered their adoption in downstream understanding applications. We present the Neural Slot Interpreter (NSI) that learns to ground and generate object semantics via slot representations. At the core of NSI is an XML-like programming language that uses simple syntax rules to organize the …

abstract abstractions adoption applications arxiv cs.ai cs.cv however interpreter interpreters object perception progress raw semantics type understanding unsupervised world