The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision

TL;DR

The paper introduces NS-CL, a neuro-symbolic model that learns visual concepts, language understanding, and semantic parsing from natural supervision, enabling flexible scene interpretation and question answering without explicit annotations.

Contribution

It presents a novel neuro-symbolic framework that jointly learns visual concepts and language parsing from paired images and questions, with strong generalization capabilities.

Findings

High accuracy in learning visual concepts and language parsing.

Effective generalization to new attributes, scenes, and questions.

Supports applications like visual question answering and image-text retrieval.

Abstract

We propose the Neuro-Symbolic Concept Learner (NS-CL), a model that learns visual concepts, words, and semantic parsing of sentences without explicit supervision on any of them; instead, our model learns by simply looking at images and reading paired questions and answers. Our model builds an object-based scene representation and translates sentences into executable, symbolic programs. To bridge the learning of two modules, we use a neuro-symbolic reasoning module that executes these programs on the latent scene representation. Analogical to human concept learning, the perception module learns visual concepts based on the language description of the object being referred to. Meanwhile, the learned visual concepts facilitate learning new words and parsing new sentences. We use curriculum learning to guide the searching over the large compositional space of images and language. Extensive experiments demonstrate the accuracy and efficiency of our model on learning visual concepts, word representations, and semantic parsing of sentences. Further, our method allows easy generalization to new object attributes, compositions, language concepts, scenes and questions, and even new program domains. It also empowers applications including visual question answering and bidirectional image-text retrieval.