VSA4VQA: Scaling a Vector Symbolic Architecture to Visual Question Answering on Natural Images

arXiv:2405.03852v1 Announce Type: new
Abstract: While Vector Symbolic Architectures (VSAs) are promising for modelling spatial cognition, their application is currently limited to artificially generated images and simple spatial queries. We propose VSA4VQA - a novel 4D implementation of VSAs that implements a mental representation of natural images for the challenging task of Visual Question Answering (VQA). VSA4VQA is the first model to scale a VSA to complex spatial queries. Our method is based on the Semantic Pointer Architecture (SPA) to …

abstract application architecture architectures arxiv cognition cs.ai cs.cv generated images implementation modelling natural novel queries question question answering representation scaling simple spatial type vector visual while