MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to
Limited Data Domains
- URL: http://arxiv.org/abs/2104.13742v2
- Date: Mon, 4 Dec 2023 08:33:55 GMT
- Title: MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to
Limited Data Domains
- Authors: Yaxing Wang, Abel Gonzalez-Garcia, Chenshen Wu, Luis Herranz, Fahad
Shahbaz Khan, Shangling Jui and Joost van de Weijer
- Abstract summary: We propose a novel knowledge transfer method for generative models based on mining the knowledge that is most beneficial to a specific target domain.
This is done using a miner network that identifies which part of the generative distribution of each pretrained GAN outputs samples closest to the target domain.
We show that the proposed method, called MineGAN, effectively transfers knowledge to domains with few target images, outperforming existing methods.
- Score: 77.46963293257912
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: GANs largely increases the potential impact of generative models. Therefore,
we propose a novel knowledge transfer method for generative models based on
mining the knowledge that is most beneficial to a specific target domain,
either from a single or multiple pretrained GANs. This is done using a miner
network that identifies which part of the generative distribution of each
pretrained GAN outputs samples closest to the target domain. Mining effectively
steers GAN sampling towards suitable regions of the latent space, which
facilitates the posterior finetuning and avoids pathologies of other methods,
such as mode collapse and lack of flexibility. Furthermore, to prevent
overfitting on small target domains, we introduce sparse subnetwork selection,
that restricts the set of trainable neurons to those that are relevant for the
target dataset. We perform comprehensive experiments on several challenging
datasets using various GAN architectures (BigGAN, Progressive GAN, and
StyleGAN) and show that the proposed method, called MineGAN, effectively
transfers knowledge to domains with few target images, outperforming existing
methods. In addition, MineGAN can successfully transfer knowledge from multiple
pretrained GANs.
Related papers
- Generative adversarial networks for data-scarce spectral applications [0.0]
We report on an application of GANs in the domain of synthetic spectral data generation.
We show that CWGANs can act as a surrogate model with improved performance in the low-data regime.
arXiv Detail & Related papers (2023-07-14T16:27:24Z) - Self-training through Classifier Disagreement for Cross-Domain Opinion
Target Extraction [62.41511766918932]
Opinion target extraction (OTE) or aspect extraction (AE) is a fundamental task in opinion mining.
Recent work focus on cross-domain OTE, which is typically encountered in real-world scenarios.
We propose a new SSL approach that opts for selecting target samples whose model output from a domain-specific teacher and student network disagrees on the unlabelled target data.
arXiv Detail & Related papers (2023-02-28T16:31:17Z) - Adaptive Domain Generalization via Online Disagreement Minimization [17.215683606365445]
Domain Generalization aims to safely transfer a model to unseen target domains.
AdaODM adaptively modifies the source model at test time for different target domains.
Results show AdaODM stably improves the generalization capacity on unseen domains.
arXiv Detail & Related papers (2022-08-03T11:51:11Z) - D3T-GAN: Data-Dependent Domain Transfer GANs for Few-shot Image
Generation [17.20913584422917]
Few-shot image generation aims at generating realistic images through training a GAN model given few samples.
A typical solution for few-shot generation is to transfer a well-trained GAN model from a data-rich source domain to the data-deficient target domain.
We propose a novel self-supervised transfer scheme termed D3T-GAN, addressing the cross-domain GANs transfer in few-shot image generation.
arXiv Detail & Related papers (2022-05-12T11:32:39Z) - META: Mimicking Embedding via oThers' Aggregation for Generalizable
Person Re-identification [68.39849081353704]
Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time.
This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
arXiv Detail & Related papers (2021-12-16T08:06:50Z) - Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training
for Road Segmentation of Remote Sensing Images [93.50240389540252]
Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials.
We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field.
Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
arXiv Detail & Related papers (2021-08-28T09:29:14Z) - Multi-Source Domain Adaptation for Object Detection [52.87890831055648]
We propose a unified Faster R-CNN based framework, termed Divide-and-Merge Spindle Network (DMSN)
DMSN can simultaneously enhance domain innative and preserve discriminative power.
We develop a novel pseudo learning algorithm to approximate optimal parameters of pseudo target subset.
arXiv Detail & Related papers (2021-06-30T03:17:20Z) - EC-GAN: Low-Sample Classification using Semi-Supervised Algorithms and
GANs [0.0]
Semi-supervised learning has been gaining attention as it allows for performing image analysis tasks such as classification with limited labeled data.
Some popular algorithms using Generative Adrial Networks (GANs) for semi-supervised classification share a single architecture for classification and discrimination.
This may require a model to converge to a separate data distribution for each task, which may reduce overall performance.
We propose a novel GAN model namely External GAN (ECGAN) that utilizes GANs and semi-supervised algorithms to improve classification in fully-supervised tasks.
arXiv Detail & Related papers (2020-12-26T05:58:00Z) - Discrepancy Minimization in Domain Generalization with Generative
Nearest Neighbors [13.047289562445242]
Domain generalization (DG) deals with the problem of domain shift where a machine learning model trained on multiple-source domains fail to generalize well on a target domain with different statistics.
Multiple approaches have been proposed to solve the problem of domain generalization by learning domain invariant representations across the source domains that fail to guarantee generalization on the shifted target domain.
We propose a Generative Nearest Neighbor based Discrepancy Minimization (GNNDM) method which provides a theoretical guarantee that is upper bounded by the error in the labeling process of the target.
arXiv Detail & Related papers (2020-07-28T14:54:25Z) - On Leveraging Pretrained GANs for Generation with Limited Data [83.32972353800633]
generative adversarial networks (GANs) can generate highly realistic images, that are often indistinguishable (by humans) from real images.
Most images so generated are not contained in a training dataset, suggesting potential for augmenting training sets with GAN-generated data.
We leverage existing GAN models pretrained on large-scale datasets to introduce additional knowledge, following the concept of transfer learning.
An extensive set of experiments is presented to demonstrate the effectiveness of the proposed techniques on generation with limited data.
arXiv Detail & Related papers (2020-02-26T21:53:36Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.