Keywords: transfer learning, diffusion probabilistic models, cross-attention, fine-tuning
TL;DR: We propose a new tuning approach for transferring pretrained diffusion probabilistic models to new tasks with limited data and training resources.
Abstract: Diffusion Probabilistic Models (DPMs) achieve impressive performance in visual generative tasks recently. However, the success of DPMs heavily relies on large amounts of data and optimization steps, which limits the application of DPMs to small datasets and limited computational resources. In this paper, we investigate transfer learning in DPMs to leverage the DPMs pretrained on large-scale datasets for generation with limited data. Firstly, we show that previous methods like training from scratch or determining the transferable parts is not suitable for the DPM due to its U-Net based denoising architecture with the external denoising timestep input. To address it, we present a condition-based tuning approach to take full advantages of existing pretrained models. Concretely, we obtain the semantic embeddings of condition images by the pretrained CLIP model, and then inject these semantic informations to the pretrained DPM via a ''Attention-NonLinear'' (ANL) module. The adaptation to a new task can be achieved by only tuning the ANL module inserted into the pretrained DPM hierarchically. To further enhance the diversity of generated images, we introduce a masked sampling strategy based on the condition mechanism. Extensive experiments validate the effectiveness and efficiency of our proposed tuning approach in generative task transfer and data augmentation for semi-supervised learning.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Generative models