# VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching

arXiv: https://arxiv.org/abs/2105.05636 · HTML: https://mlsanity.com/paper/2105.05636/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 98 references that are in the map.
- First posted on arXiv 12 May 2021.

## Builds on (most cited first, 30 of 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [MAttNet: Modular Attention Network for Referring Expression Comprehension](https://mlsanity.com/paper/1801.08186/) (2018)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [TransVG: End-to-End Visual Grounding with Transformers](https://mlsanity.com/paper/2104.08541/) (2021)
- [Cross-Modal Self-Attention Network for Referring Image Segmentation](https://mlsanity.com/paper/1904.04745/) (2019)
- [Segmentation from Natural Language Expressions](https://mlsanity.com/paper/1603.06180/) (2016)
- [Modeling Context Between Objects for Referring Expression Understanding](https://mlsanity.com/paper/1608.00525/) (2016)
- [Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments](https://mlsanity.com/paper/1811.12354/) (2018)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation](https://mlsanity.com/paper/2003.08813/) (2020)
- [A Fast and Accurate One-Stage Approach to Visual Grounding](https://mlsanity.com/paper/1908.06354/) (2019)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [Counterfactual Samples Synthesizing for Robust Visual Question Answering](https://mlsanity.com/paper/2003.06576/) (2020)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [Learning Deep Structure-Preserving Image-Text Embeddings](https://mlsanity.com/paper/1511.06078/) (2015)
- [Improving One-stage Visual Grounding by Recursive Sub-query Construction](https://mlsanity.com/paper/2008.01059/) (2020)

## Built on by (most cited first, 2 of 2)

- [Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding](https://mlsanity.com/paper/2403.11463/) (2024)
- [TreePrompt: Learning to Compose Tree Prompts for Explainable Visual Grounding](https://mlsanity.com/paper/2305.11497/) (2023)

## Abstract (arXiv)

The prevailing framework for matching multimodal inputs is based on a two-stage process: 1) detecting proposals with an object detector and 2) matching text queries with proposals. Existing two-stage solutions mostly focus on the matching step. In this paper, we argue that these methods overlook an obvious mismatch between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i.e., query-agnostic), hoping that the proposals contain all instances mentioned in the text query (i.e., query-aware). Due to this mismatch, chances are that proposals relevant to the text query are suppressed during the filtering process, which in turn bounds the matching performance. To this end, we propose VL-NMS, which is the first method to yield query-aware proposals at the first stage. VL-NMS regards all mentioned instances as critical objects, and introduces a lightweight module to predict a score for aligning each proposal with a critical object. These scores can guide the NMS operation to filter out proposals irrelevant to the text query, increasing the recall of critical objects, resulting in a significantly improved matching performance. Since VL-NMS is agnostic to the matching step, it can be easily integrated into any state-of-the-art two-stage matching methods. We validate the effectiveness of VL-NMS on two multimodal matching tasks, namely referring expression grounding and image-text matching. Extensive ablation studies on several baselines and benchmarks consistently demonstrate the superiority of VL-NMS.