Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908427810242560 |
|---|---|
| author | Ren, Jie Li, Yaxin Zeng, Shenglai Xu, Han Lyu, Lingjuan Xing, Yue Tang, Jiliang |
| author_facet | Ren, Jie Li, Yaxin Zeng, Shenglai Xu, Han Lyu, Lingjuan Xing, Yue Tang, Jiliang |
| contents | Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images from their training data, raising tremendous concerns about potential copyright infringement and privacy risks. In our study, we provide a novel perspective to understand this memorization phenomenon by examining its relationship with cross-attention mechanisms. We reveal that during memorization, the cross-attention tends to focus disproportionately on the embeddings of specific tokens. The diffusion model is overfitted to these token embeddings, memorizing corresponding training images. To elucidate this phenomenon, we further identify and discuss various intrinsic findings of cross-attention that contribute to memorization. Building on these insights, we introduce an innovative approach to detect and mitigate memorization in diffusion models. The advantage of our proposed method is that it will not compromise the speed of either the training or the inference processes in these models while preserving the quality of generated images. Our code is available at https://github.com/renjie3/MemAttn . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11052 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention Ren, Jie Li, Yaxin Zeng, Shenglai Xu, Han Lyu, Lingjuan Xing, Yue Tang, Jiliang Computer Vision and Pattern Recognition Cryptography and Security Recent advancements in text-to-image diffusion models have demonstrated their remarkable capability to generate high-quality images from textual prompts. However, increasing research indicates that these models memorize and replicate images from their training data, raising tremendous concerns about potential copyright infringement and privacy risks. In our study, we provide a novel perspective to understand this memorization phenomenon by examining its relationship with cross-attention mechanisms. We reveal that during memorization, the cross-attention tends to focus disproportionately on the embeddings of specific tokens. The diffusion model is overfitted to these token embeddings, memorizing corresponding training images. To elucidate this phenomenon, we further identify and discuss various intrinsic findings of cross-attention that contribute to memorization. Building on these insights, we introduce an innovative approach to detect and mitigate memorization in diffusion models. The advantage of our proposed method is that it will not compromise the speed of either the training or the inference processes in these models while preserving the quality of generated images. Our code is available at https://github.com/renjie3/MemAttn . |
| title | Unveiling and Mitigating Memorization in Text-to-image Diffusion Models through Cross Attention |
| topic | Computer Vision and Pattern Recognition Cryptography and Security |
| url | https://arxiv.org/abs/2403.11052 |