Mitigating Semantic Collapse in Generative Personalization with a Surprisingly Simple Test-Time Embedding Adjustment
Mitigating Semantic Collapse in Generative Personalization with a Surprisingly Simple Test-Time Embedding Adjustment
In this paper, we investigate the semantic collapsing problem in generative personalization, an under-explored topic where the learned visual concept ($V^*$) gradually shifts from its original textual meaning and comes to dominate other concepts in multi-concept input prompts. This issue not only reduces the semantic richness of complex input prompts like "a photo of $V^*$ wearing glasses and playing guitar" into simpler, less contextually rich forms such as "a photo of $V^*$" but also leads to simplified output images that fail to capture the intended concept. We identify the root cause as unconstrained optimisation, which allows the learned embedding $V^*$ to drift arbitrarily in the embedding space, both in direction and magnitude. To address this, we propose a simple yet effective training-free method that adjusts the magnitude and direction of pre-trained embedding at inference time, effectively mitigating the semantic collapsing problem. Our method is broadly applicable across different personalization methods and demonstrates significant improvements in text-image alignment in diverse use cases. Our code is anonymously published at https://anonymous.4open.science/r/Embedding-Adjustment.
Anh Bui、Trang Vu、Trung Le、Junae Kim、Tamas Abraham、Rollin Omari、Amar Kaur、Dinh Phung
计算技术、计算机技术
Anh Bui,Trang Vu,Trung Le,Junae Kim,Tamas Abraham,Rollin Omari,Amar Kaur,Dinh Phung.Mitigating Semantic Collapse in Generative Personalization with a Surprisingly Simple Test-Time Embedding Adjustment[EB/OL].(2025-06-27)[2025-07-16].https://arxiv.org/abs/2506.22685.点此复制
评论