理解並緩解擴散模型中的複製行為

摘要

由穩定擴散等擴散模型生成的圖像越來越普遍。最近的研究甚至訴訟表明，這些模型往往會在未經使用者察覺的情況下複製其訓練數據。在本文中，我們首先分析了文本到圖像擴散模型中這個記憶問題。儘管廣泛認為訓練集中的重複圖像是推斷時內容複製的原因，但我們觀察到模型的文本條件設置同樣扮演著重要角色。事實上，我們在實驗中發現，無條件模型通常不會發生數據複製，而在文本條件下則很常見。受到我們發現的啟發，我們提出了幾種減少訓練和推斷時數據複製的技術，通過在訓練集中對圖像標題進行隨機化和增強。

English

Images generated by diffusion models like Stable Diffusion are increasingly widespread. Recent works and even lawsuits have shown that these models are prone to replicating their training data, unbeknownst to the user. In this paper, we first analyze this memorization problem in text-to-image diffusion models. While it is widely believed that duplicated images in the training set are responsible for content replication at inference time, we observe that the text conditioning of the model plays a similarly important role. In fact, we see in our experiments that data replication often does not happen for unconditional models, while it is common in the text-conditional case. Motivated by our findings, we then propose several techniques for reducing data replication at both training and inference time by randomizing and augmenting image captions in the training set.

理解並緩解擴散模型中的複製行為

Understanding and Mitigating Copying in Diffusion Models

摘要

Support