Neuro-Symbolic VQA: A review from the perspective of AGI desiderata
This work provides a critical perspective for researchers in AI and ML by evaluating VQA models beyond benchmarks, though it is incremental as a review.
The paper reviews neuro-symbolic approaches to visual question answering (VQA) by assessing how well they meet AGI desiderata, highlighting that these criteria often conflict in practice.
An ultimate goal of the AI and ML fields is artificial general intelligence (AGI); although such systems remain science fiction, various models exhibit aspects of AGI. In this work, we look at neuro-symbolic (NS)approaches to visual question answering (VQA) from the perspective of AGI desiderata. We see how well these systems meet these desiderata, and how the desiderata often pull the scientist in opposing directions. It is my hope that through this work we can temper model evaluation on benchmarks with a discussion of the properties of these systems and their potential for future extension.