# Dynamic Contrastive Distillation for Image-Text Retrieval

arXiv: https://arxiv.org/abs/2207.01426 · HTML: https://mlsanity.com/paper/2207.01426/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 77 references that are in the map.
- First posted on arXiv 4 Jul 2022.

## Builds on (most cited first, 30 of 47)

- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [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)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [An Empirical Study of Training End-to-End Vision-and-Language Transformers](https://mlsanity.com/paper/2111.02387/) (2021)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [Unsupervised Embedding Learning via Invariant and Spreading Instance Feature](https://mlsanity.com/paper/1904.03436/) (2019)
- [Visual Semantic Reasoning for Image-Text Matching](https://mlsanity.com/paper/1909.02701/) (2019)
- [Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation](https://mlsanity.com/paper/2105.08919/) (2021)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [Gradient Harmonized Single-stage Detector](https://mlsanity.com/paper/1811.05181/) (2018)

## Built on by (most cited first, 14 of 14)

- [KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model](https://mlsanity.com/paper/2506.20923/) (2025)
- [DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture](https://mlsanity.com/paper/2409.03550/) (2024)
- [Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?](https://mlsanity.com/paper/2308.12898/) (2023)
- [Active Data Curation Effectively Distills Large-Scale Multimodal Models](https://mlsanity.com/paper/2411.18674/) (2024)
- [Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation](https://mlsanity.com/paper/2510.15304/) (2025)
- [Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation](https://mlsanity.com/paper/2412.10761/) (2024)
- [Prompt-Learning for Cross-Lingual Relation Extraction](https://mlsanity.com/paper/2304.10354/) (2023)
- [Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models](https://mlsanity.com/paper/2409.12512/) (2024)
- [Prototype Perturbation for Relaxing Alignment Constraints in Backward-Compatible Learning](https://mlsanity.com/paper/2503.14824/) (2025)
- [MCAD: Multi-teacher Cross-modal Alignment Distillation for efficient image-text retrieval](https://mlsanity.com/paper/2310.19654/) (2023)
- [2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA](https://mlsanity.com/paper/2604.23935/) (2026)
- [Dual Stage Stylization Modulation for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2304.09347/) (2023)
- [A Layered Self-Supervised Knowledge Distillation Framework for Efficient Multimodal Learning on the Edge](https://mlsanity.com/paper/2506.07055/) (2025)
- [TopKD: Top-scaled Knowledge Distillation](https://mlsanity.com/paper/2508.04539/) (2025)

## Abstract (arXiv)

Although the vision-and-language pretraining (VLP) equipped cross-modal image-text retrieval (ITR) has achieved remarkable progress in the past two years, it suffers from a major drawback: the ever-increasing size of VLP models restricts its deployment to real-world search scenarios (where the high latency is unacceptable). To alleviate this problem, we present a novel plug-in dynamic contrastive distillation (DCD) framework to compress the large VLP models for the ITR task. Technically, we face the following two challenges: 1) the typical uni-modal metric learning approach is difficult to directly apply to the cross-modal tasks, due to the limited GPU memory to optimize too many negative samples during handling cross-modal fusion features. 2) it is inefficient to static optimize the student network from different hard samples, which have different effects on distillation learning and student network optimization. We try to overcome these challenges from two points. First, to achieve multi-modal contrastive learning, and balance the training costs and effects, we propose to use a teacher network to estimate the difficult samples for students, making the students absorb the powerful knowledge from pre-trained teachers, and master the knowledge from hard samples. Second, to dynamic learn from hard sample pairs, we propose dynamic distillation to dynamically learn samples of different difficulties, from the perspective of better balancing the difficulty of knowledge and students' self-learning ability. We successfully apply our proposed DCD strategy to two state-of-the-art vision-language pretrained models, i.e. ViLT and METER. Extensive experiments on MS-COCO and Flickr30K benchmarks show the effectiveness and efficiency of our DCD framework. Encouragingly, we can speed up the inference at least 129× compared to the existing ITR models.