# D'ej`a Vu Memorization in Vision-Language Models

arXiv: https://arxiv.org/abs/2402.02103 · HTML: https://mlsanity.com/paper/2402.02103/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 3 Feb 2024.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Scaling Language-Image Pre-training via Masking](https://mlsanity.com/paper/2212.00794/) (2022)
- [SemDeDup: Data-efficient learning at web-scale through semantic deduplication](https://mlsanity.com/paper/2303.09540/) (2023)
- [Demystifying CLIP Data](https://mlsanity.com/paper/2309.16671/) (2023)
- [Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training](https://mlsanity.com/paper/2301.02280/) (2023)
- [Analyzing Information Leakage of Updates to Natural Language Models](https://mlsanity.com/paper/1912.07942/) (2019)
- [A Study of Face Obfuscation in ImageNet](https://mlsanity.com/paper/2103.06191/) (2021)
- [Are Attribute Inference Attacks Just Imputation?](https://mlsanity.com/paper/2209.01292/) (2022)
- [Do SSL Models Have D'ej`a Vu? A Case of Unintended Memorization in Self-supervised Learning](https://mlsanity.com/paper/2304.13850/) (2023)
- [D'ej`a Vu: an empirical evaluation of the memorization properties of ConvNets](https://mlsanity.com/paper/1809.06396/) (2018)
- [Combing for Credentials: Active Pattern Extraction from Smart Reply](https://mlsanity.com/paper/2207.10802/) (2022)

## Built on by (most cited first, 9 of 9)

- [An Introduction to Vision-Language Modeling](https://mlsanity.com/paper/2405.17247/) (2024)
- [Membership Inference Attacks Against Vision-Language Models](https://mlsanity.com/paper/2501.18624/) (2025)
- [Eureka: Evaluating and Understanding Large Foundation Models](https://mlsanity.com/paper/2409.10566/) (2024)
- [Seeing Through Their Eyes: Evaluating Visual Perspective Taking in Vision Language Models](https://mlsanity.com/paper/2409.12969/) (2024)
- [Understanding Depth and Height Perception in Large Visual-Language Models](https://mlsanity.com/paper/2408.11748/) (2024)
- [LeakyCLIP: Extracting Training Data from CLIP](https://mlsanity.com/paper/2508.00756/) (2025)
- [DIS-CO: Discovering Copyrighted Content in VLMs Training Data](https://mlsanity.com/paper/2502.17358/) (2025)
- [MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning](https://mlsanity.com/paper/2606.22220/) (2026)
- [COMPASS: Membership Inference Attack Against Vision Large Language Models via Adaptive Noise Calibration](https://mlsanity.com/paper/2610.17332/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) have emerged as the state-of-the-art representation learning solution, with myriads of downstream applications such as image classification, retrieval and generation. A natural question is whether these models memorize their training data, which also has implications for generalization. We propose a new method for measuring memorization in VLMs, which we call d'ej`a vu memorization. For VLMs trained on image-caption pairs, we show that the model indeed retains information about individual objects in the training images beyond what can be inferred from correlations or the image caption. We evaluate d'ej`a vu memorization at both sample and population level, and show that it is significant for OpenCLIP trained on as many as 50M image-caption pairs. Finally, we show that text randomization considerably mitigates memorization while only moderately impacting the model's downstream task performance.