# HiVLP: Hierarchical Vision-Language Pre-Training for Fast Image-Text Retrieval

arXiv: https://arxiv.org/abs/2205.12105 · HTML: https://mlsanity.com/paper/2205.12105/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 43 of its 51 references that are in the map.
- First posted on arXiv 24 May 2022.

## Placed in

- Multimodal LLMs / vision-language models / [Document understanding and multimodal RAG](https://mlsanity.com/mllm/document-understanding-and-multimodal-rag/)

## Builds on (most cited first, 30 of 43)

- [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)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [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)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [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)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [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)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [An Empirical Study of Training End-to-End Vision-and-Language Transformers](https://mlsanity.com/paper/2111.02387/) (2021)
- [Multi30K: Multilingual English-German Image Descriptions](https://mlsanity.com/paper/1605.00459/) (2016)

## Built on by (most cited first, 4 of 4)

- [Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey](https://mlsanity.com/paper/2302.10035/) (2023)
- [From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities](https://mlsanity.com/paper/2311.00308/) (2023)
- [Aligning Forest and Trees in Images & Long Captions for Visually Grounded Understanding](https://mlsanity.com/paper/2602.02977/) (2026)
- [Multi-Granularity and Multi-modal Feature Interaction Approach for Text Video Retrieval](https://mlsanity.com/paper/2407.12798/) (2024)

## Abstract (arXiv)

In the past few years, the emergence of vision-language pre-training (VLP) has brought cross-modal retrieval to a new era. However, due to the latency and computation demand, it is commonly challenging to apply VLP in a real-time online retrieval system. To alleviate the defect, this paper proposes a Hierarchical Vision-Language Pre-Training (HiVLP) for fast Image-Text Retrieval (ITR). Specifically, we design a novel hierarchical retrieval objective, which uses the representation of different dimensions for coarse-to-fine ITR, i.e., using low-dimensional representation for large-scale coarse retrieval and high-dimensional representation for small-scale fine retrieval. We evaluate our proposed HiVLP on two popular image-text retrieval benchmarks, i.e., Flickr30k and COCO. Extensive experiments demonstrate that our HiVLP not only has fast inference speed but also can be easily scaled to large-scale ITR scenarios. The detailed results show that HiVLP is 1,427~120,649× faster than the fusion-based model UNITER and 2~5 faster than the fastest embedding-based model LightingDot in different candidate scenarios. It also achieves about +4.9 AR on COCO and +3.8 AR on Flickr30K than LightingDot and achieves comparable performance with the state-of-the-art (SOTA) fusion-based model METER.