Research Area:  Machine Learning

Abstract:

Text-to-image generative models can produce diverse high-quality images of concepts with a text prompt, which have demonstrated excellent ability in image generation, image translation, etc. We in this work study the problem of synthesizing instantiations of a users own concepts in a never-ending manner, i.e., create your world, where the new concepts from user are quickly learned with a few examples. To achieve this goal, we propose a Lifelong text-to-image Diffusion Model (L 2 DM), which intends to overcome knowledge “catastrophic forgetting” for the past encountered concepts, and semantic “catastrophic neglecting” for one or more concepts in the text prompt. In respect of knowledge “catastrophic forgetting”, our L 2 DM framework devises a task-aware memory enhancement module and an elastic-concept distillation module, which could respectively safeguard the knowledge of both prior concepts and each past personalized concept. When generating images with a user text prompt, the solution to semantic “catastrophic neglecting” is that a concept attention artist module can alleviate the semantic neglecting from concept aspect, and an orthogonal attention module can reduce the semantic binding from attribute aspect. To the end, our model can generate more faithful image across a range of continual text prompts in terms of both qualitative and quantitative metrics, when comparing with the related state-of-the-art models.

Keywords:  

Author(s) Name:  Gan Sun; Wenqi Liang; Jiahua Dong; Jun Li; Zhengming Ding; Yang Cong

Publisher name:  IEEE

DOI:  10.1109/TPAMI.2024.3382753

Volume Information:  Volume: 46, Pages: 6454 - 6470

Paper Link:   https://ieeexplore.ieee.org/document/10489849