Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion
This addresses the problem of generating diverse and accurate images with minimal samples for researchers and practitioners in computer vision, representing an incremental improvement over existing few-shot generation techniques.
The paper tackles the challenge of few-shot image generation by proposing Conditional Relaxing Diffusion Inversion (CRDI), a training-free method that reconstructs target images and expands diversity, achieving performance equal to state-of-the-art methods and mitigating overfitting and catastrophic forgetting.
In the field of Few-Shot Image Generation (FSIG) using Deep Generative Models (DGMs), accurately estimating the distribution of target domain with minimal samples poses a significant challenge. This requires a method that can both capture the broad diversity and the true characteristics of the target domain distribution. We present Conditional Relaxing Diffusion Inversion (CRDI), an innovative `training-free' approach designed to enhance distribution diversity in synthetic image generation. Distinct from conventional methods, CRDI does not rely on fine-tuning based on only a few samples. Instead, it focuses on reconstructing each target image instance and expanding diversity through few-shot learning. The approach initiates by identifying a Sample-wise Guidance Embedding (SGE) for the diffusion model, which serves a purpose analogous to the explicit latent codes in certain Generative Adversarial Network (GAN) models. Subsequently, the method involves a scheduler that progressively introduces perturbations to the SGE, thereby augmenting diversity. Comprehensive experiments demonstrates that our method surpasses GAN-based reconstruction techniques and equals state-of-the-art (SOTA) FSIG methods in performance. Additionally, it effectively mitigates overfitting and catastrophic forgetting, common drawbacks of fine-tuning approaches.