paper-with-me

홈 › Papers

A Fourier Transform Framework for Domain Adaptation

2024-03-12 · Le Luo, Bingrong Xu, Qingyong Zhang, Cheng Lian, Jie Luo

By using unsupervised domain adaptation (UDA), knowledge can be transferred from a label-rich source domain to a target domain that contains relevant information but lacks labels. Many existing UDA algorithms suffer from directly using raw images as input, resulting in models that overly focus on redundant information and exhibit poor generalization capability. To address this issue, we attempt to improve the performance of unsupervised domain adaptation by employing the Fourier method (FTF).Specifically, FTF is inspired by the amplitude of Fourier spectra, which primarily preserves low-level statistical information. In FTF, we effectively incorporate low-level information from the target domain into the source domain by fusing the amplitudes of both domains in the Fourier domain. Additionally, we observe that extracting features from batches of images can eliminate redundant information while retaining class-specific features relevant to the task. Building upon this observation, we apply the Fourier Transform at the data stream level for the first time. To further align multiple sources of data, we introduce the concept of correlation alignment. To evaluate the effectiveness of our FTF method, we conducted evaluations on four benchmark datasets for domain adaptation, including Office-31, Office-Home, ImageCLEF-DA, and Office-Caltech. Our results demonstrate superior performance.

📄 PDF Abstract BibTeX arXiv:2403.07798

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationUnsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Focus 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Parameter-Efficient Fine-Tuning with Discrete Fourier Transform

2024-05-05 · Ziqi Gao, Qichao Wang, Aochuan Chen, Zijing Liu 외

Low-rank adaptation~(LoRA) has recently gained much interest in fine-tuning foundation models. It effectively reduces the number of trainable parameters by incorporating low-rank matrices $A$ and $B$ to represent the wei…

image-classificationImage ClassificationNatural Language Understandingparameter-efficient fine-tuning+1

FourierMoE: Fourier Mixture-of-Experts Adaptation of Large Language Models

2026-04-02 · Juyong Jiang, Fan Wang, Hong Qi, Sunghun Kim 외 arxiv

Parameter-efficient fine-tuning (PEFT) has emerged as a crucial paradigm for adapting large language models (LLMs) under constrained computational budgets. However, standard PEFT methods often struggle in multi-task fine…

parameter-efficient fine-tuning

Domain Adaptation on Graphs by Learning Aligned Graph Bases

2018-03-14 · Mehmet Pilanci, Elif Vural

A common assumption in semi-supervised learning with graph models is that the class label function varies smoothly on the data graph, resulting in the rather strict prior that the label function has low-frequency content…

Domain AdaptationGeneral Classification

FDA: Fourier Domain Adaptation for Semantic Segmentation

2020-04-11 · CVPR 2020 6 · Yanchao Yang, Stefano Soatto

We describe a simple method for unsupervised domain adaptation, whereby the discrepancy between the source and target distributions is reduced by swapping the low-frequency spectrum of one with the other. We illustrate t…

Domain AdaptationSegmentationSemantic SegmentationUnsupervised Domain Adaptation

Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification

2023-06-05 · Yuhao Huang, Xin Yang, Xiaoqiong Huang, Xinrui Zhou 외

Deep classifiers may encounter significant performance degradation when processing unseen testing data from varying centers, vendors, and protocols. Ensuring the robustness of deep models against these domain shifts is c…

Robust classificationTest-time Adaptation