Déjà Vu Memorization in Vision-Language Models

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 déjà 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 déjà 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.

Prior work has looked into this problem for image-only representation models [Meehan et al., 2023] by measuring whether the model can predict the foreground of an image (e.g, black swan) beyond simple correlations based simply on its background (e.g, water). However, such simple solutions do not apply here. VLMs have two separate modalities -text and image, and the data sets used to train and evaluate them are considerably more complex than the simple foreground-background structure of ImageNet (see Figure 6 for an example). A consequence is that the image and text modalities 38th Conference on Neural Information Processing Systems (NeurIPS 2024).