CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes

TL;DR

The paper introduces a graph parser library for the CLEVR dataset that extracts object attributes and relationships, enabling geometric learning and improving tasks like language grounding and interpretability in vision-language models.

Contribution

It provides an extensible, easy-to-integrate graph parser library for CLEVR that facilitates structural representations for geometric learning and downstream applications.

Findings

Enables structural graph representations for CLEVR scenes

Supports seamless integration with GNN libraries

Accelerates research in language-grounded visual reasoning

Abstract

The CLEVR dataset has been used extensively in language grounded visual reasoning in Machine Learning (ML) and Natural Language Processing (NLP) domains. We present a graph parser library for CLEVR, that provides functionalities for object-centric attributes and relationships extraction, and construction of structural graph representations for dual modalities. Structural order-invariant representations enable geometric learning and can aid in downstream tasks like language grounding to vision, robotics, compositionality, interpretability, and computational grammar construction. We provide three extensible main components - parser, embedder, and visualizer that can be tailored to suit specific learning setups. We also provide out-of-the-box functionality for seamless integration with popular deep graph neural network (GNN) libraries. Additionally, we discuss downstream usage and applications of the library, and how it accelerates research for the NLP research community.