# VLDeformer: Vision-Language Decomposed Transformer for Fast Cross-Modal Retrieval

arXiv: https://arxiv.org/abs/2110.11338 · HTML: https://mlsanity.com/paper/2110.11338/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 20 Oct 2021.

## Builds on (most cited first, 25 of 25)

- [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)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [A Multiscale Visualization of Attention in the Transformer Model](https://mlsanity.com/paper/1906.05714/) (2019)
- [Dual-Path Convolutional Image-Text Embeddings with Instance Loss](https://mlsanity.com/paper/1711.05535/) (2017)
- [ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data](https://mlsanity.com/paper/2001.07966/) (2020)
- [Similarity Reasoning and Filtration for Image-Text Matching](https://mlsanity.com/paper/2101.01368/) (2021)
- [Learning Two-Branch Neural Networks for Image-Text Matching Tasks](https://mlsanity.com/paper/1704.03470/) (2017)
- [IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval](https://mlsanity.com/paper/2003.03772/) (2020)
- [Dual Attention Networks for Multimodal Reasoning and Matching](https://mlsanity.com/paper/1611.00471/) (2016)
- [Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models](https://mlsanity.com/paper/1711.06420/) (2017)
- [LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval](https://mlsanity.com/paper/2103.08784/) (2021)
- [Linking Image and Text with 2-Way Nets](https://mlsanity.com/paper/1608.07973/) (2016)

## Built on by (most cited first, 6 of 6)

- [All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment](https://mlsanity.com/paper/2307.03373/) (2023)
- [Delving Deeper: Hierarchical Visual Perception for Robust Video-Text Retrieval](https://mlsanity.com/paper/2601.12768/) (2026)
- [FashionSAP: Symbols and Attributes Prompt for Fine-grained Fashion Vision-Language Pre-training](https://mlsanity.com/paper/2304.05051/) (2023)
- [Collaborative Group: Composed Image Retrieval via Consensus Learning from Noisy Annotations](https://mlsanity.com/paper/2306.02092/) (2023)
- [FiCo-ITR: bridging fine-grained and coarse-grained image-text retrieval for comparative performance analysis](https://mlsanity.com/paper/2407.20114/) (2024)
- [An Enhanced Large Language Model For Cross Modal Query Understanding System Using DL-KeyBERT Based CAZSSCL-MPGPT](https://mlsanity.com/paper/2502.17000/) (2025)

## Abstract (arXiv)

Cross-model retrieval has emerged as one of the most important upgrades for text-only search engines (SE). Recently, with powerful representation for pairwise text-image inputs via early interaction, the accuracy of vision-language (VL) transformers has outperformed existing methods for text-image retrieval. However, when the same paradigm is used for inference, the efficiency of the VL transformers is still too low to be applied in a real cross-modal SE. Inspired by the mechanism of human learning and using cross-modal knowledge, this paper presents a novel Vision-Language Decomposed Transformer (VLDeformer), which greatly increases the efficiency of VL transformers while maintaining their outstanding accuracy. By the proposed method, the cross-model retrieval is separated into two stages: the VL transformer learning stage, and the VL decomposition stage. The latter stage plays the role of single modal indexing, which is to some extent like the term indexing of a text SE. The model learns cross-modal knowledge from early-interaction pre-training and is then decomposed into an individual encoder. The decomposition requires only small target datasets for supervision and achieves both 1000+ times acceleration and less than 0.6% average recall drop. VLDeformer also outperforms state-of-the-art visual-semantic embedding methods on COCO and Flickr30k.