Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05651 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916678407815168 |
|---|---|
| author | Kokhlikyan, Narine Jayaraman, Bargav Bordes, Florian Guo, Chuan Chaudhuri, Kamalika |
| author_facet | Kokhlikyan, Narine Jayaraman, Bargav Bordes, Florian Guo, Chuan Chaudhuri, Kamalika |
| contents | Recent research has shown that representation learning models may accidentally memorize their training data. For example, the déjà vu method shows that for certain representation learning models and training images, it is sometimes possible to correctly predict the foreground label given only the representation of the background - better than through dataset-level correlations. However, their measurement method requires training two models - one to estimate dataset-level correlations and the other to estimate memorization. This multiple model setup becomes infeasible for large open-source models. In this work, we propose alternative simple methods to estimate dataset-level correlations, and show that these can be used to approximate an off-the-shelf model's memorization ability without any retraining. This enables, for the first time, the measurement of memorization in pre-trained open-source image representation and vision-language representation models. Our results show that different ways of measuring memorization yield very similar aggregate results. We also find that open-source models typically have lower aggregate memorization than similar models trained on a subset of the data. The code is available both for vision and vision language models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05651 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Measuring Déjà vu Memorization Efficiently Kokhlikyan, Narine Jayaraman, Bargav Bordes, Florian Guo, Chuan Chaudhuri, Kamalika Machine Learning Computer Vision and Pattern Recognition Recent research has shown that representation learning models may accidentally memorize their training data. For example, the déjà vu method shows that for certain representation learning models and training images, it is sometimes possible to correctly predict the foreground label given only the representation of the background - better than through dataset-level correlations. However, their measurement method requires training two models - one to estimate dataset-level correlations and the other to estimate memorization. This multiple model setup becomes infeasible for large open-source models. In this work, we propose alternative simple methods to estimate dataset-level correlations, and show that these can be used to approximate an off-the-shelf model's memorization ability without any retraining. This enables, for the first time, the measurement of memorization in pre-trained open-source image representation and vision-language representation models. Our results show that different ways of measuring memorization yield very similar aggregate results. We also find that open-source models typically have lower aggregate memorization than similar models trained on a subset of the data. The code is available both for vision and vision language models. |
| title | Measuring Déjà vu Memorization Efficiently |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.05651 |