Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation (original) (raw)

MineGAN: Effective Knowledge Transfer From GANs to Target Domains With Few Images

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020

One of the attractive characteristics of deep neural networks is their ability to transfer knowledge obtained in one domain to other related domains. As a result, high-quality networks can be trained in domains with relatively little training data. This property has been extensively studied for discriminative networks but has received significantly less attention for generative models. Given the often enormous effort required to train GANs, both computationally as well as in the dataset collection, the re-use of pretrained GANs is a desirable objective. 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. We perform experiments on several complex datasets using various GAN architectures (BigGAN, Progressive GAN) 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. Our code is

Data Instance Prior for Transfer Learning in GANs

ArXiv, 2020

Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images. However, this gain in performance depends on the availability of a large amount of training data. In limited data regimes, training typically diverges, and therefore the generated samples are of low quality and lack diversity. Previous works have addressed training in low data setting by leveraging transfer learning and data augmentation techniques. We propose a novel transfer learning method for GANs in the limited data domain by leveraging informative data prior derived from self-supervised/supervised pre-trained networks trained on a diverse source domain. We perform experiments on several standard vision datasets using various GAN architectures (BigGAN, SNGAN, StyleGAN2) to demonstrate that the proposed method effectively transfers knowledge to domains with few target images, outperforming existing state-of-the-art techniques in terms of image quality and d...

Conditional Adversarial Domain Adaptation

2018

Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may struggle to align different domains of multimodal distributions that are native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. Experiments testify that the proposed approach exceeds the state-of-the-art results on five benchmark datasets.

Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency

arXiv (Cornell University), 2021

Most modern unsupervised domain adaptation (UDA) approaches are rooted in domain alignment, i.e., learning to align source and target features to learn a target domain classifier using source labels. In semi-supervised domain adaptation (SSDA), when the learner can access few target domain labels, prior approaches have followed UDA theory to use domain alignment for learning. We show that the case of SSDA is different and a good target classifier can be learned without needing alignment. We use selfsupervised pretraining (via rotation prediction) and consistency regularization to achieve well separated target clusters, aiding in learning a low error target classifier. With our Pretraining and Consistency (PAC) approach, we achieve state of the art target accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets. PAC, while using simple techniques, performs remarkably well on large and challenging SSDA benchmarks like DomainNet and Visda-17, often outperforming recent state of the art by sizeable margins. Code for our experiments can be found at https://github.com/venkatesh-saligrama/PAC.

Unsupervised Domain Adaptation using Generative Models and Self-ensembling

Cornell University - arXiv, 2018

Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can generalize across multiple domain shifts, so that this model can adapt from a single source to multiple targets. This can be achieved by randomizing the generation of the data of various styles to mitigate the domain mismatch. First, we present a new adaptation to the CycleGAN model to produce stochastic style transfer between two image batches of different domains. Second, we enhance the classifier performance by using a self-ensembling technique with a teacher and student model to train on both original and generated data. Finally, we present experimental results on three datasets Office-31, Office-Home, and Visual Domain adaptation. The results suggest that selfensembling is better than simple data augmentation with the newly generated data and a single model trained this way can have the best performance across all different transfer tasks. 1. Showing that GAN networks can help make a model

Adversarial Domain Adaptation via Category Transfer

2019 International Joint Conference on Neural Networks (IJCNN)

Adversarial domain adaptation has achieved some success in learning transferable feature representations and reducing distribution discrepancy between source and target domains. However, existing approaches mainly focus on alignment of global source and target distributions without considering complex structures in categories underlying different distributions, resulting in domain confusion and the mix of distinguishable structures. In this paper, we propose an adversarial domain adaptation via category transfer (ADACT) approach for unsupervised domain adaptation (UDA). ADACT first captures multi-category information through training source and target feature generators as well as a label predictor. Secondly, it uses multi-category domain critic networks to categorywisely estimate Wasserstein distances across domains. Then it learns category-invariant feature representations by finelygrained matching different data distributions with the estimated Wasserstein distances. The adaptation can be achieved by the standard back-propagation training approach with this two-step iteration. The effectiveness of ADACT is demonstrated since it outperforms several state-of-the-art UDA methods on common domain adaptation datasets.

CLDA: Contrastive Learning for Semi-Supervised Domain Adaptation

Cornell University - arXiv, 2021

Unsupervised Domain Adaptation (UDA) aims to align the labeled source distribution with the unlabeled target distribution to obtain domain invariant predictive models. However, the application of well-known UDA approaches does not generalize well in Semi-Supervised Domain Adaptation (SSDA) scenarios where few labeled samples from the target domain are available. This paper proposes a simple Contrastive Learning framework for semi-supervised Domain Adaptation (CLDA) that attempts to bridge the intra-domain gap between the labeled and unlabeled target distributions and the inter-domain gap between source and unlabeled target distribution in SSDA. We suggest employing class-wise contrastive learning to reduce the inter-domain gap and instance-level contrastive alignment between the original(input image) and strongly augmented unlabeled target images to minimize the intra-domain discrepancy. We have empirically shown that both of these modules complement each other to achieve superior performance. Experiments on three well-known domain adaptation benchmark datasets, namely DomainNet, Office-Home, and Office31, demonstrate the effectiveness of our approach. CLDA achieves state-of-the-art results on all the above datasets. 35th Conference on Neural Information Processing Systems (NeurIPS 2021).

S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels

2020

Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process. Conditional GANs (cGANs) provide a mechanism to control the generation process by conditioning the output on a user defined input. Although training GANs requires only unsupervised data, training cGANs requires labelled data which can be very expensive to obtain. We propose a framework for semi-supervised training of cGANs which utilizes sparse labels to learn the conditional mapping, and at the same time leverages a large amount of unsupervised data to learn the unconditional distribution. We demonstrate effectiveness of our method on multiple datasets and different conditional tasks.

MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains

arXiv (Cornell University), 2021

Given the often enormous effort required to train GANs, both computationally as well as in dataset collection, the re-use of pretrained 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. Our code is available at: https://github.com/yaxingwang/MineGAN.

Targeted adversarial discriminative domain adaptation

Geospatial Informatics XI, 2021

Domain adaptation is a technology enabling aided target recognition and other algorithms for environments and targets with data or labeled data that is scarce. Recent advances in unsupervised domain adaptation have demonstrated excellent performance but only when the domain shift is relatively small. We proposed targeted adversarial discriminative domain adaptation (T-ADDA), a semi-supervised domain adaptation method that extends the ADDA framework. By providing at least one labeled target image per class, used as a cue to guide the adaption, T-ADDA significantly boosts the performance of ADDA and is applicable to the challenging scenario in which the sets of targets in the source and target domains are not the same. The efficacy of T-ADDA is demonstrated by cross-domain, cross-sensor, and cross-target experiments using the common digits datasets and several aerial image datasets. Results demonstrate an average increase of 15% improvement with T-ADDA over ADDA using just a few labeled images when adapting to a small domain shift and afforded a 60% improvement when adapting to large domain shifts. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.