# Learning to Assemble Neural Module Tree Networks for Visual Grounding

arXiv: https://arxiv.org/abs/1812.03299 · HTML: https://mlsanity.com/paper/1812.03299/

## Key facts

- Cited by 140 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2018.

## Built on by (most cited first, 30 of 140)

- [CRIS: CLIP-Driven Referring Image Segmentation](https://mlsanity.com/paper/2111.15174/) (2021)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [GRES: Generalized Referring Expression Segmentation](https://mlsanity.com/paper/2306.00968/) (2023)
- [What does CLIP know about a red circle? Visual prompt engineering for VLMs](https://mlsanity.com/paper/2304.06712/) (2023)
- [Universal Instance Perception as Object Discovery and Retrieval](https://mlsanity.com/paper/2303.06674/) (2023)
- [Referring Transformer: A One-step Approach to Multi-task Visual Grounding](https://mlsanity.com/paper/2106.03089/) (2021)
- [Multi-View Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2204.02174/) (2022)
- [SeqTR: A Simple yet Universal Network for Visual Grounding](https://mlsanity.com/paper/2203.16265/) (2022)
- [RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data](https://mlsanity.com/paper/2210.12634/) (2022)
- [VLT: Vision-Language Transformer and Query Generation for Referring Segmentation](https://mlsanity.com/paper/2210.15871/) (2022)
- [3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection](https://mlsanity.com/paper/2204.06272/) (2022)
- [Locate then Segment: A Strong Pipeline for Referring Image Segmentation](https://mlsanity.com/paper/2103.16284/) (2021)
- [Referring Multi-Object Tracking](https://mlsanity.com/paper/2303.03366/) (2023)
- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Open-vocabulary Object Segmentation with Diffusion Models](https://mlsanity.com/paper/2301.05221/) (2023)
- [ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance](https://mlsanity.com/paper/2303.16894/) (2023)
- [Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning](https://mlsanity.com/paper/2205.00272/) (2022)
- [Joint Visual Grounding and Tracking with Natural Language Specification](https://mlsanity.com/paper/2303.12027/) (2023)
- [Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding](https://mlsanity.com/paper/2203.15442/) (2022)
- [Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding](https://mlsanity.com/paper/2104.04386/) (2021)
- [Toward Visual Grounding: A Survey](https://mlsanity.com/paper/2412.20206/) (2024)
- [Exploring Sequence Feature Alignment for Domain Adaptive Detection Transformers](https://mlsanity.com/paper/2107.12636/) (2021)
- [Visual Grounding with Transformers](https://mlsanity.com/paper/2105.04281/) (2021)
- [TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer](https://mlsanity.com/paper/2206.06619/) (2022)
- [Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2209.13306/) (2022)
- [GREC: Generalized Referring Expression Comprehension](https://mlsanity.com/paper/2308.16182/) (2023)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching](https://mlsanity.com/paper/2111.08919/) (2021)
- [Multi-Modal Mutual Attention and Iterative Interaction for Referring Image Segmentation](https://mlsanity.com/paper/2305.15302/) (2023)
- [3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation](https://mlsanity.com/paper/2308.16632/) (2023)

## Abstract (arXiv)

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.