Customize Your Own Paired Data via Few-shot Way
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:WU2K6N27record.jsonopen to challenge →
read the original abstract
Existing solutions to image editing tasks suffer from several issues. Though achieving remarkably satisfying generated results, some supervised methods require huge amounts of paired training data, which greatly limits their usages. The other unsupervised methods take full advantage of large-scale pre-trained priors, thus being strictly restricted to the domains where the priors are trained on and behaving badly in out-of-distribution cases. The task we focus on is how to enable the users to customize their desired effects through only few image pairs. In our proposed framework, a novel few-shot learning mechanism based on the directional transformations among samples is introduced and expands the learnable space exponentially. Adopting a diffusion model pipeline, we redesign the condition calculating modules in our model and apply several technical improvements. Experimental results demonstrate the capabilities of our method in various cases.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.