Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation
This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled target sample is assumed to be available for model adaptation. Driven by such single sample, our method LearnAug-UDA learns how to augment source data, making it perceptually similar to the target. As a result, a classifier trained on such augmented data will generalize well for the target domain. To achieve this, we designed an encoder-decoder architecture that exploits a perceptual loss and style transfer strategies to augment the source data. Our method achieves state-of-the-art performance on two well-known Domain Adaptation benchmarks, DomainNet and VisDA. The project code is available at https://github.com/IIT-PAVIS/LearnAug-UDA
Code (1)
Tasks
Data AugmentationDecoderDomain AdaptationOne-shot Unsupervised Domain AdaptationStyle TransferUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Target-driven One-Shot Unsupervised Domain Adaptation
In this paper, we introduce a novel framework for the challenging problem of One-Shot Unsupervised Domain Adaptation (OSUDA), which aims to adapt to a target domain with only a single unlabeled target sample. Unlike exis…
Domain AdaptationOne-shot Unsupervised Domain AdaptationUnsupervised Domain AdaptationAAPL: Adding Attributes to Prompt Learning for Vision-Language Models
Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of pr…
Data AugmentationDomain GeneralizationFew-Shot LearningImage Augmentation+2Learning Instance-Specific Adaptation for Cross-Domain Segmentation
We propose a test-time adaptation method for cross-domain image segmentation. Our method is simple: Given a new unseen instance at test time, we adapt a pre-trained model by conducting instance-specific BatchNorm (statis…
Data AugmentationDomain AdaptationDomain GeneralizationImage Segmentation+4Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
We aim to build image generation models that generalize to new domains from few examples. To this end, we first investigate the generalization properties of classic image generators, and discover that autoencoders genera…
Image GenerationUnsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-depende…
ClusteringMeta-LearningUnsupervised Few-Shot Image Classification