Document Type

Conference Proceeding

Publication Title

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Abstract

Generative Adversarial Networks (GANs) rely heavily on large-scale training data for training high-quality image generation models. With limited training data, the GAN discriminator often suffers from severe overfitting which directly leads to degraded generation especially in generation diversity. Inspired by the recent advances in knowledge distillation (KD), we propose KD-DLGAN, a knowledge-distillation based generation framework that introduces pre-trained vision-language models for training effective data-limited generation models. KD-DLGAN consists of two innovative designs. The first is aggregated generative KD that mitigates the discriminator overfitting by challenging the discriminator with harder learning tasks and distilling more generalizable knowledge from the pre-trained models. The second is correlated generative KD that improves the generation diversity by distilling and preserving the diverse image-text correlation within the pre-trained models. Extensive experiments over multiple benchmarks show that KD-DLGAN achieves superior image generation with limited training data. In addition, KD-DLGAN complements the state-of-the-art with consistent and substantial performance gains. Note that codes will be released.

First Page

3872

Last Page

3882

DOI

10.1109/CVPR52729.2023.00377

Publication Date

8-22-2023

Keywords

Training, Correlation, Image synthesis, Diversity reception, Training data, Performance gain, Generative adversarial networks

Comments

Preprint version from arXiv

CC BY-NC-SA

Uploaded on June 4, 2024

Download

Share

COinS