paper-with-me

홈 › Papers

Few-shot Image Generation with Elastic Weight Consolidation

2020-12-04 · NeurIPS 2020 12 · Yijun Li, Richard Zhang, Jingwan Lu, Eli Shechtman

Few-shot image generation seeks to generate more data of a given domain, with only few available training examples. As it is unreasonable to expect to fully infer the distribution from just a few observations (e.g., emojis), we seek to leverage a large, related source domain as pretraining (e.g., human faces). Thus, we wish to preserve the diversity of the source domain, while adapting to the appearance of the target. We adapt a pretrained model, without introducing any additional parameters, to the few examples of the target domain. Crucially, we regularize the changes of the weights during this adaptation, in order to best preserve the information of the source dataset, while fitting the target. We demonstrate the effectiveness of our algorithm by generating high-quality results of different target domains, including those with extremely few examples (e.g., <10). We also analyze the performance of our method with respect to some important factors, such as the number of examples and the dissimilarity between the source and target domain.

📄 PDF Abstract BibTeX arXiv:2012.02780

Code (0)

등록된 구현이 없습니다.

Tasks

10-shot image generationDiversityImage Generation

Similar Papers 제목 키워드 기반

EVCL: Elastic Variational Continual Learning with Weight Consolidation

2024-06-23 · Hunar Batra, Ronald Clark

Continual learning aims to allow models to learn new tasks without forgetting what has been learned before. This work introduces Elastic Variational Continual Learning with Weight Consolidation (EVCL), a novel hybrid mod…

Continual LearningIncremental Learning

Elastic Weight Consolidation (EWC): Nuts and Bolts

2021-05-10 · Abhishek Aich

In this report, we present a theoretical support of the continual learning method \textbf{Elastic Weight Consolidation}, introduced in paper titled `Overcoming catastrophic forgetting in neural networks'. Being one of th…

Continual Learning

On Quadratic Penalties in Elastic Weight Consolidation

2017-12-11 · Ferenc Huszár

Elastic weight consolidation (EWC, Kirkpatrick et al, 2017) is a novel algorithm designed to safeguard against catastrophic forgetting in neural networks. EWC can be seen as an approximation to Laplace propagation (Eskin…

Mitigating the Diminishing Effect of Elastic Weight Consolidation

2022-10-01 · COLING 2022 10 · Canasai Kruengkrai, Junichi Yamagishi

Elastic weight consolidation (EWC, Kirkpatrick et al. 2017) is a promising approach to addressing catastrophic forgetting in sequential training. We find that the effect of EWC can diminish when fine-tuning large-scale p…

Fact CheckingNatural Language Inference

Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

2018-02-08 · Xialei Liu, Marc Masana, Luis Herranz, Joost Van de Weijer 외

In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios. Our technique is based on a network reparameterization that approximately diagonalizes the Fisher Informatio…

Lifelong learning