Progressively Unfreezing Perceptual GAN
Generative adversarial networks (GANs) are widely used in image generation tasks, yet the generated images are usually lack of texture details. In this paper, we propose a general framework, called Progressively Unfreezing Perceptual GAN (PUPGAN), which can generate images with fine texture details. Particularly, we propose an adaptive perceptual discriminator with a pre-trained perceptual feature extractor, which can efficiently measure the discrepancy between multi-level features of the generated and real images. In addition, we propose a progressively unfreezing scheme for the adaptive perceptual discriminator, which ensures a smooth transfer process from a large scale classification task to a specified image generation task. The qualitative and quantitative experiments with comparison to the classical baselines on three image generation tasks, i.e. single image super-resolution, paired image-to-image translation and unpaired image-to-image translation demonstrate the superiority of PUPGAN over the compared approaches.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationImage Super-ResolutionImage-to-Image TranslationSuper-ResolutionTranslationSimilar Papers 제목 키워드 기반
Early Period of Training Impacts Adaptation for Out-of-Distribution Generalization: An Empirical Study
Prior research shows that differences in the early period of neural network training significantly impact the performance of in-distribution (ID) data of tasks. Yet, the implications of early learning dynamics on out-of-…
Out-of-Distribution GeneralizationFUN with Fisher: Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing
Standard fine-tuning of language models typically performs well on in-distribution data, but suffers with generalization to distribution shifts. In this work, we aim to improve the generalization of adapter-based cross-l…
Cross-Lingual TransferTransfer LearningGradient Sparsification For Masked Fine-Tuning of Transformers
Fine-tuning pretrained self-supervised language models is widely adopted for transfer learning to downstream tasks. Fine-tuning can be achieved by freezing gradients of the pretrained network and only updating gradients …
Transfer LearningGradient Sparsification For \emph{Masked Fine-Tuning} of Transformers
Fine-tuning masked language models is widely adopted for transfer learning to downstream tasks and can be achieved by (1) freezing gradients of the pretrained network or only updating gradients of a newly added classific…
Transfer LearningXLM-RFine-Tuning Without Forgetting: Adaptation of YOLOv8 Preserves COCO Performance
The success of large pre-trained object detectors hinges on their adaptability to diverse downstream tasks. While fine-tuning is the standard adaptation method, specializing these models for challenging fine-grained doma…