# COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval

arXiv: https://arxiv.org/abs/2204.07441 · HTML: https://mlsanity.com/paper/2204.07441/

## Key facts

- Cited by 33 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 46 of its 58 references that are in the map.
- First posted on arXiv 15 Apr 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 46)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [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)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [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)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts](https://mlsanity.com/paper/2102.08981/) (2021)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [ActBERT: Learning Global-Local Video-Text Representations](https://mlsanity.com/paper/2011.07231/) (2020)

## Built on by (most cited first, 30 of 33)

- [MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining](https://mlsanity.com/paper/2208.12262/) (2022)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey](https://mlsanity.com/paper/2302.10035/) (2023)
- [SegViTv2: Exploring Efficient and Continual Semantic Segmentation with Plain Vision Transformers](https://mlsanity.com/paper/2306.06289/) (2023)
- [Efficient Vision-Language Pretraining with Visual Concepts and Hierarchical Alignment](https://mlsanity.com/paper/2208.13628/) (2022)
- [Global and Local Semantic Completion Learning for Vision-Language Pre-training](https://mlsanity.com/paper/2306.07096/) (2023)
- [Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control](https://mlsanity.com/paper/2402.17535/) (2024)
- [LGDN: Language-Guided Denoising Network for Video-Language Modeling](https://mlsanity.com/paper/2209.11388/) (2022)
- [A Multi-Modal Context Reasoning Approach for Conditional Inference on Joint Textual and Visual Clues](https://mlsanity.com/paper/2305.04530/) (2023)
- [Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval](https://mlsanity.com/paper/2403.05105/) (2024)
- [Multimodal foundation models are better simulators of the human brain](https://mlsanity.com/paper/2208.08263/) (2022)
- [Misalign, Contrast then Distill: Rethinking Misalignments in Language-Image Pretraining](https://mlsanity.com/paper/2312.12661/) (2023)
- [Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning](https://mlsanity.com/paper/2405.16996/) (2024)
- [Leveraging per Image-Token Consistency for Vision-Language Pre-training](https://mlsanity.com/paper/2211.15398/) (2022)
- [NEUCORE: Neural Concept Reasoning for Composed Image Retrieval](https://mlsanity.com/paper/2310.01358/) (2023)
- [EA-VTR: Event-Aware Video-Text Retrieval](https://mlsanity.com/paper/2407.07478/) (2024)
- [RoCOCO: Robustness Benchmark of MS-COCO to Stress-test Image-Text Matching Models](https://mlsanity.com/paper/2304.10727/) (2023)
- [CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image](https://mlsanity.com/paper/2412.12906/) (2024)
- [Generalized Contrastive Learning for Universal Multimodal Retrieval](https://mlsanity.com/paper/2509.25638/) (2025)
- [Masked Contrastive Reconstruction for Cross-modal Medical Image-Report Retrieval](https://mlsanity.com/paper/2312.15840/) (2023)
- [RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval](https://mlsanity.com/paper/2210.06881/) (2022)
- [How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?](https://mlsanity.com/paper/2407.07479/) (2024)
- [LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models](https://mlsanity.com/paper/2312.00674/) (2023)
- [GMM-Based Comprehensive Feature Extraction and Relative Distance Preservation For Few-Shot Cross-Modal Retrieval](https://mlsanity.com/paper/2505.13306/) (2025)
- [Selectively Hard Negative Mining for Alleviating Gradient Vanishing in Image-Text Matching](https://mlsanity.com/paper/2303.00181/) (2023)
- [LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval](https://mlsanity.com/paper/2302.02908/) (2023)
- [VITR: Augmenting Vision Transformers with Relation-Focused Learning for Cross-Modal Information Retrieval](https://mlsanity.com/paper/2302.06350/) (2023)
- [Ambiguity-Aware and High-Order Relation Learning for Multi-Grained Image-Text Matching](https://mlsanity.com/paper/2507.09256/) (2025)
- [LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrieval](https://mlsanity.com/paper/2511.06268/) (2025)
- [Efficient Image-Text Retrieval via Keyword-Guided Pre-Screening](https://mlsanity.com/paper/2303.07740/) (2023)

## Abstract (arXiv)

Large-scale single-stream pre-training has shown dramatic performance in image-text retrieval. Regrettably, it faces low inference efficiency due to heavy attention layers. Recently, two-stream methods like CLIP and ALIGN with high inference efficiency have also shown promising performance, however, they only consider instance-level alignment between the two streams (thus there is still room for improvement). To overcome these limitations, we propose a novel COllaborative Two-Stream vision-language pretraining model termed COTS for image-text retrieval by enhancing cross-modal interaction. In addition to instance level alignment via momentum contrastive learning, we leverage two extra levels of cross-modal interactions in our COTS: (1) Token-level interaction - a masked visionlanguage modeling (MVLM) learning objective is devised without using a cross-stream network module, where variational autoencoder is imposed on the visual encoder to generate visual tokens for each image. (2) Task-level interaction - a KL-alignment learning objective is devised between text-to-image and image-to-text retrieval tasks, where the probability distribution per task is computed with the negative queues in momentum contrastive learning. Under a fair comparison setting, our COTS achieves the highest performance among all two-stream methods and comparable performance (but with 10,800X faster in inference) w.r.t. the latest single-stream methods. Importantly, our COTS is also applicable to text-to-video retrieval, yielding new state-ofthe-art on the widely-used MSR-VTT dataset.