Learning to Assemble Neural Module Tree Networks for Visual Grounding

TL;DR

This paper introduces NMTree, a modular neural network that grounds natural language in images by following sentence dependency trees, enabling explainable and compositional visual reasoning.

Contribution

It proposes a novel neural module tree network that aligns visual grounding with sentence dependency parsing, improving interpretability and performance.

Findings

Outperforms state-of-the-art methods on multiple benchmarks.

Provides explainable visual grounding through detailed module attention.

Effectively handles parsing errors with end-to-end training.

Abstract

Visual grounding, a task to ground (i.e., localize) natural language in images, essentially requires composite visual reasoning. However, existing methods over-simplify the composite nature of language into a monolithic sentence embedding or a coarse composition of subject-predicate-object triplet. In this paper, we propose to ground natural language in an intuitive, explainable, and composite fashion as it should be. In particular, we develop a novel modular network called Neural Module Tree network (NMTree) that regularizes the visual grounding along the dependency parsing tree of the sentence, where each node is a neural module that calculates visual attention according to its linguistic feature, and the grounding score is accumulated in a bottom-up direction where as needed. NMTree disentangles the visual grounding from the composite reasoning, allowing the former to only focus on primitive and easy-to-generalize patterns. To reduce the impact of parsing errors, we train the modules and their assembly end-to-end by using the Gumbel-Softmax approximation and its straight-through gradient estimator, accounting for the discrete nature of module assembly. Overall, the proposed NMTree consistently outperforms the state-of-the-arts on several benchmarks. Qualitative results show explainable grounding score calculation in great detail.