CVOct 27, 2022

Few-shot Image Generation via Masked Discrimination

arXiv:2210.15194v325 citationsh-index: 14
Originality Incremental advance
AI Analysis

This addresses the problem of diversity degradation in GANs for few-shot image generation, which is incremental but improves on existing adaptation techniques.

The paper tackles overfitting in few-shot image generation by introducing masked discrimination and a cross-domain consistency loss, achieving higher quality and greater diversity than prior methods.

Few-shot image generation aims to generate images of high quality and great diversity with limited data. However, it is difficult for modern GANs to avoid overfitting when trained on only a few images. The discriminator can easily remember all the training samples and guide the generator to replicate them, leading to severe diversity degradation. Several methods have been proposed to relieve overfitting by adapting GANs pre-trained on large source domains to target domains using limited real samples. This work presents a novel approach to realize few-shot GAN adaptation via masked discrimination. Random masks are applied to features extracted by the discriminator from input images. We aim to encourage the discriminator to judge various images which share partially common features with training samples as realistic. Correspondingly, the generator is guided to generate diverse images instead of replicating training samples. In addition, we employ a cross-domain consistency loss for the discriminator to keep relative distances between generated samples in its feature space. It strengthens global image discrimination and guides adapted GANs to preserve more information learned from source domains for higher image quality. The effectiveness of our approach is demonstrated both qualitatively and quantitatively with higher quality and greater diversity on a series of few-shot image generation tasks than prior methods.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes