# Distilled Dual-Encoder Model for Vision-Language Understanding

arXiv: https://arxiv.org/abs/2112.08723 · HTML: https://mlsanity.com/paper/2112.08723/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 65 of its 84 references that are in the map.
- First posted on arXiv 16 Dec 2021.

## Builds on (most cited first, 30 of 65)

- [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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [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)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [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)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)

## Built on by (most cited first, 22 of 22)

- [Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2311.13165/) (2023)
- [BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning](https://mlsanity.com/paper/2206.08657/) (2022)
- [EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning](https://mlsanity.com/paper/2210.07795/) (2022)
- [ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency](https://mlsanity.com/paper/2302.10307/) (2023)
- [FashionViL: Fashion-Focused Vision-and-Language Representation Learning](https://mlsanity.com/paper/2207.08150/) (2022)
- [Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment](https://mlsanity.com/paper/2208.13628/) (2022)
- [Active Data Curation Effectively Distills Large-Scale Multimodal Models](https://mlsanity.com/paper/2411.18674/) (2024)
- [MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation](https://mlsanity.com/paper/2308.04829/) (2023)
- [Module-wise Adaptive Distillation for Multimodality Foundation Models](https://mlsanity.com/paper/2310.04550/) (2023)
- [TV-TREES: Multimodal Entailment Trees for Neuro-Symbolic Video Reasoning](https://mlsanity.com/paper/2402.19467/) (2024)
- [CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information](https://mlsanity.com/paper/2409.13199/) (2024)
- [SmartTrim: Adaptive Tokens and Attention Pruning for Efficient Vision-Language Models](https://mlsanity.com/paper/2305.15033/) (2023)
- [How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?](https://mlsanity.com/paper/2407.07479/) (2024)
- [EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models](https://mlsanity.com/paper/2506.00479/) (2025)
- [MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval](https://mlsanity.com/paper/2310.19654/) (2023)
- [Vision Encoder-Decoder Models for AI Coaching](https://mlsanity.com/paper/2311.16161/) (2023)
- [E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer](https://mlsanity.com/paper/2311.17267/) (2023)
- [sDREAMER: Self-distilled Mixture-of-Modality-Experts Transformer for Automatic Sleep Staging](https://mlsanity.com/paper/2501.16329/) (2025)
- [Manager: Aggregating Insights from Unimodal Experts in Two-Tower VLMs and MLLMs](https://mlsanity.com/paper/2506.11515/) (2025)
- [Robust Audio-Text Retrieval via Cross-Modal Attention and Hybrid Loss](https://mlsanity.com/paper/2604.23323/) (2026)
- [Query, Align, and Distill: Navigation-Aware Cross-Modal Interaction for Efficient Vision-and-Language Navigation](https://mlsanity.com/paper/2609.33097/) (2026)
- [TerraAgent: Demonstration-Grounded Multi-Agent Reasoning for Long-Context Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2610.12517/) (2026)

## Abstract (arXiv)

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than fusion-encoder models and enable the pre-computation of images and text during inference. However, the shallow interaction module used in dual-encoder models is insufficient to handle complex vision-language understanding tasks. In order to learn deep interactions of images and text, we introduce cross-modal attention distillation, which uses the image-to-text and text-to-image attention distributions of a fusion-encoder model to guide the training of our dual-encoder model. In addition, we show that applying the cross-modal attention distillation for both pre-training and fine-tuning stages achieves further improvements. Experimental results demonstrate that the distilled dual-encoder model achieves competitive performance for visual reasoning, visual entailment and visual question answering tasks while enjoying a much faster inference speed than fusion-encoder models. Our code and models will be publicly available at https://github.com/kugwzk/Distilled-DualEncoder.