AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation

TL;DR

This paper introduces AdAM, a novel method for few-shot image generation that adapts kernel modulation to better handle varying degrees of similarity between source and target domains, outperforming existing methods.

Contribution

The paper proposes Adaptation-Aware kernel Modulation (AdAM), a new approach that considers target domain adaptation, improving FSIG performance across diverse domain proximities.

Findings

AdAM achieves state-of-the-art results in various FSIG setups.

Existing methods perform poorly when source-target domain proximity is relaxed.

AdAM outperforms baseline methods in challenging domain adaptation scenarios.

Abstract

Few-shot image generation (FSIG) aims to learn to generate new and diverse images given few (e.g., 10) training samples. Recent work has addressed FSIG by leveraging a GAN pre-trained on a large-scale source domain and adapting it to the target domain with few target samples. Central to recent FSIG methods are knowledge preservation criteria, which select and preserve a subset of source knowledge to the adapted model. However, a major limitation of existing methods is that their knowledge preserving criteria consider only source domain/task and fail to consider target domain/adaptation in selecting source knowledge, casting doubt on their suitability for setups of different proximity between source and target domain. Our work makes two contributions. Firstly, we revisit recent FSIG works and their experiments. We reveal that under setups which assumption of close proximity between source and target domains is relaxed, many existing state-of-the-art (SOTA) methods which consider only source domain in knowledge preserving perform no better than a baseline method. As our second contribution, we propose Adaptation-Aware kernel Modulation (AdAM) for general FSIG of different source-target domain proximity. Extensive experiments show that AdAM consistently achieves SOTA performance in FSIG, including challenging setups where source and target domains are more apart.