Online Exemplar Fine-Tuning for Image-to-Image Translation

11/18/2020
by   Taewon Kang, et al.
5

Existing techniques to solve exemplar-based image-to-image translation within deep convolutional neural networks (CNNs) generally require a training phase to optimize the network parameters on domain-specific and task-specific benchmarks, thus having limited applicability and generalization ability. In this paper, we propose a novel framework, for the first time, to solve exemplar-based translation through an online optimization given an input image pair, called online exemplar fine-tuning (OEFT), in which we fine-tune the off-the-shelf and general-purpose networks to the input image pair themselves. We design two sub-networks, namely correspondence fine-tuning and multiple GAN inversion, and optimize these network parameters and latent codes, starting from the pre-trained ones, with well-defined loss functions. Our framework does not require the off-line training phase, which has been the main challenge of existing methods, but the pre-trained networks to enable optimization in online. Experimental results prove that our framework is effective in having a generalization power to unseen image pairs and clearly even outperforms the state-of-the-arts needing the intensive training phase.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 6

page 7

page 8

research
12/12/2021

Deep Translation Prior: Test-time Training for Photorealistic Style Transfer

Recent techniques to solve photorealistic style transfer within deep con...
research
01/07/2022

Repurposing Existing Deep Networks for Caption and Aesthetic-Guided Image Cropping

We propose a novel optimization framework that crops a given image based...
research
03/26/2021

Multiple GAN Inversion for Exemplar-based Image-to-Image Translation

Existing state-of-the-art techniques in exemplar-based image-to-image tr...
research
11/24/2022

CycleGANWM: A CycleGAN watermarking method for ownership verification

Due to the proliferation and widespread use of deep neural networks (DNN...
research
12/12/2021

Unsupervised Domain-Specific Deblurring using Scale-Specific Attention

In the literature, coarse-to-fine or scale-recurrent approach i.e. progr...
research
11/21/2016

Image-to-Image Translation with Conditional Adversarial Networks

We investigate conditional adversarial networks as a general-purpose sol...
research
06/30/2018

G2C: A Generator-to-Classifier Framework Integrating Multi-Stained Visual Cues for Pathological Glomerulus Classification

Pathological glomerulus classification plays a key role in the diagnosis...

Please sign up or login with your details

Forgot password? Click here to reset