Spectral Adversarial MixUp for Few-Shot Unsupervised Domain Adaptation

2023-09-03 · Jiajin Zhang, Hanqing Chao, Amit Dhurandhar, Pin-Yu Chen, Ali Tajer, Yangyang Xu, Pingkun Yan

Domain shift is a common problem in clinical applications, where the training images (source domain) and the test images (target domain) are under different distributions. Unsupervised Domain Adaptation (UDA) techniques have been proposed to adapt models trained in the source domain to the target domain. However, those methods require a large number of images from the target domain for model training. In this paper, we propose a novel method for Few-Shot Unsupervised Domain Adaptation (FSUDA), where only a limited number of unlabeled target domain samples are available for training. To accomplish this challenging task, first, a spectral sensitivity map is introduced to characterize the generalization weaknesses of models in the frequency domain. We then developed a Sensitivity-guided Spectral Adversarial MixUp (SAMix) method to generate target-style images to effectively suppresses the model sensitivity, which leads to improved model generalizability in the target domain. We demonstrated the proposed method and rigorously evaluated its performance on multiple tasks using several public datasets.

📄 PDF Abstract BibTeX arXiv:2309.01207

Code (1)

RPIDIAL/SAMix 공식 구현 pytorch

Tasks

Domain AdaptationSensitivityUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

Unsupervised Domain Adaptation for COVID-19 Information Service with Contrastive Adversarial Domain Mixup

2022-10-06 · Huimin Zeng, Zhenrui Yue, Ziyi Kou, Lanyu Shang 외

In the real-world application of COVID-19 misinformation detection, a fundamental challenge is the lack of the labeled COVID data to enable supervised end-to-end training of the models, especially at the early stage of t…

Contrastive Learning Domain Adaptation Misinformation Unsupervised Domain Adaptation

Improve Unsupervised Domain Adaptation with Mixup Training

2020-01-03 · Shen Yan, Huan Song, Nanxiang Li, Lincan Zou 외

Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversaria…

Activity Recognition Domain Adaptation Domain Generalization Human Activity Recognition+3

A Pairwise DomMix Attentive Adversarial Network for Unsupervised Domain Adaptive Object Detection

2024-07-03 · Jie Shao, Jiacheng Wu, Wenzhong Shen, Cheng Yang

Unsupervised Domain Adaptive Object Detection (DAOD) could adapt a model trained on a source domain to an unlabeled target domain for object detection. Existing unsupervised DAOD methods usually perform feature alignment…

object-detection Object Detection

Dual Mixup Regularized Learning for Adversarial Domain Adaptation

2020-07-07 · ECCV 2020 8 · Yuan Wu, Diana Inkpen, Ahmed El-Roby

Recent advances on unsupervised domain adaptation (UDA) rely on adversarial learning to disentangle the explanatory and transferable features for domain adaptation. However, there are two issues with the existing methods…

Domain Adaptation Unsupervised Domain Adaptation

Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model

2026-01-30 · Naeem Paeedeh, Mahardhika Pratama, Ary Shiddiqi, Zehong Cao 외 arxiv

Although cross-domain few-shot learning (CDFSL) for hyper-spectral image (HSI) classification has attracted significant research interest, existing works often rely on an unrealistic data augmentation procedure in the fo…

Hyperspectral Image Classification cross-domain few-shot learning Data Augmentation Domain Adaptation