# How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?

arXiv: https://arxiv.org/abs/2407.07479 · HTML: https://mlsanity.com/paper/2407.07479/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [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)
- [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)
- [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)
- [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)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [Large-Scale Adversarial Training for Vision-and-Language Representation Learning](https://mlsanity.com/paper/2006.06195/) (2020)
- [Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers](https://mlsanity.com/paper/2004.00849/) (2020)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [Visual Semantic Reasoning for Image-Text Matching](https://mlsanity.com/paper/1909.02701/) (2019)
- [Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation](https://mlsanity.com/paper/2010.02666/) (2020)
- [Learning the Best Pooling Strategy for Visual Semantic Embedding](https://mlsanity.com/paper/2011.04305/) (2020)
- [Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers](https://mlsanity.com/paper/2103.16553/) (2021)
- [Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO](https://mlsanity.com/paper/2004.15020/) (2020)
- [LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval](https://mlsanity.com/paper/2103.08784/) (2021)
- [COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval](https://mlsanity.com/paper/2204.07441/) (2022)
- [Distilled Dual-Encoder Model for Vision-Language Understanding](https://mlsanity.com/paper/2112.08723/) (2021)
- [LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval](https://mlsanity.com/paper/2203.05465/) (2022)

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

- [Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions](https://mlsanity.com/paper/2503.05186/) (2025)
- [Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale](https://mlsanity.com/paper/2608.25735/) (2026)
- [Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding](https://mlsanity.com/paper/2511.08978/) (2025)
- [Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning](https://mlsanity.com/paper/2603.01696/) (2026)

## Abstract (arXiv)

Dominant dual-encoder models enable efficient image-text retrieval but suffer from limited accuracy while the cross-encoder models offer higher accuracy at the expense of efficiency. Distilling cross-modality matching knowledge from cross-encoder to dual-encoder provides a natural approach to harness their strengths. Thus we investigate the following valuable question: how to make cross-encoder a good teacher for dual-encoder? Our findings are threefold:(1) Cross-modal similarity score distribution of cross-encoder is more concentrated while the result of dual-encoder is nearly normal making vanilla logit distillation less effective. However ranking distillation remains practical as it is not affected by the score distribution.(2) Only the relative order between hard negatives conveys valid knowledge while the order information between easy negatives has little significance.(3) Maintaining the coordination between distillation loss and dual-encoder training loss is beneficial for knowledge transfer. Based on these findings we propose a novel Contrastive Partial Ranking Distillation (CPRD) method which implements the objective of mimicking relative order between hard negative samples with contrastive learning. This approach coordinates with the training of the dual-encoder effectively transferring valid knowledge from the cross-encoder to the dual-encoder. Extensive experiments on image-text retrieval and ranking tasks show that our method surpasses other distillation methods and significantly improves the accuracy of dual-encoder.