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 the method in semantic segmentation, where densely annotated images are aplenty in one domain (synthetic data), but difficult to obtain in another (real images). Current state-of-the-art methods are complex, some requiring adversarial optimization to render the backbone of a neural network invariant to the discrete domain selection variable. Our method does not require any training to perform the domain alignment, just a simple Fourier Transform and its inverse. Despite its simplicity, it achieves state-of-the-art performance in the current benchmarks, when integrated into a relatively standard semantic segmentation model. Our results indicate that even simple procedures can discount nuisance variability in the data that more sophisticated methods struggle to learn away.
The following paper is a reproducibility report for "FDA: Fourier Domain Adaptation for Semantic Segmentation" published in the CVPR 2020 as part of the ML Reproducibility Challenge 2020. The original code was made available by the author. The well-commented version of the code containing all ablation studies performed derived from the original code along with WANDB integration is available at <github.com/thefatbandit/FDA> with proper instructions to execute experiments in README.
HOT: Harmonic-Constrained Optimal Transport for Remote Photoplethysmography Domain Adaptation
VNU University of Engineering and Technology, Hanoi, Vietnam（越南河内国立大学工程与技术大学）；VinUni-Illinois Smart Health Center, VinUniversity, Hanoi, Vietnam（VinUni-Illinois智慧健康中心，VinUniversity，越南河内）；College of Engineering and Computer Science, VinUniversity, Hanoi, Vietnam（VinUniversity工程与计算机科学学院，越南河内）；Center for Innovations in Health Sciences, VinUniversity, Hanoi, Vietnam（VinUniversity健康科学创新中心，越南河内）
Fourier Domain Adaptation for Traffic Light Detection in Adverse Weather
Manipal Institute of Technology（曼尼帕尔理工学院）；Manipal Academy of Higher Education（曼尼帕尔高等教育学院）；Wells Fargo International Solutions Private Limited（富国国际解决方案私人有限公司）
Singtel Cognitive and Artificial Intelligence Lab for Enterprises（Singtel企业认知与人工智能实验室）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Unsupervised domain adaptation (UDA) involves a supervised loss in a labeled source domain and an unsupervised loss in an unlabeled target domain, which often faces more severe overfitting (than classical supervised learning) as the supervised source loss has clear domain gap and the unsupervised target loss is often noisy due to the lack of annotations. This paper presents RDA, a robust domain adaptation technique that introduces adversarial attacking to mitigate overfitting in UDA. We achieve robust domain adaptation by a novel Fourier adversarial attacking (FAA) method that allows large mag…
National University of Singapore（新加坡国立大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe several significant challenges. First, the target domain data is highly insufficient, making most existing domain adaptation methods ineffective. Second, object detection involves simultaneous localization and classification, further complicating the model adaptation process. Third, the model suffers from over-adaptation (similar to overfitting when training wi…
FVP: Fourier Visual Prompting for Source-Free Unsupervised Domain Adaptation of Medical Image Segmentation
Beihang University（北京航空航天大学）；Zhejiang Lab（之江实验室）；Singapore University of Technology and Design（新加坡科技设计大学）；BioMind Technology Center（BioMind技术中心）；Zhongguancun Laboratory（中关村实验室）
Samsung AI Center Cambridge（三星剑桥人工智能中心）；University of Edinburgh（爱丁堡大学）
We tackle the domain generalisation (DG) problem by posing it as a domain adaptation (DA) task where we adversarially synthesise the worst-case target domain and adapt a model to that worst-case domain, thereby improving the model's robustness. To synthesise data that is challenging yet semantics-preserving, we generate Fourier amplitude images and combine them with source domain phase images, exploiting the widely believed conjecture from signal processing that amplitude spectra mainly determines image style, while phase data mainly captures image semantics. To synthesise a worst-case domain …
Philips Research（飞利浦研究院）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术学院）
Generalizability of deep learning models may be severely affected by the difference in the distributions of the train (source domain) and the test (target domain) sets, e.g., when the sets are produced by different hardware. As a consequence of this domain shift, a certain model might perform well on data from one clinic, and then fail when deployed in another. We propose a very light and transparent approach to perform test-time domain adaptation. The idea is to substitute the target low-frequency Fourier space components that are deemed to reflect the style of an image. To maximize the perfo…
With the FDA approval of Artificial Intelligence (AI) for point-of-care clinical diagnoses, model generalizability is of the utmost importance as clinical decision-making must be domain-agnostic. A method of tackling the problem is to increase the dataset to include images from a multitude of domains; while this technique is ideal, the security requirements of medical data is a major limitation. Additionally, researchers with developed tools benefit from the addition of open-sourced data, but are limited by the difference in domains. Herewith, we investigated the implementation of a Cycle-Cons…
Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentation
The Chinese University of Hong Kong（香港中文大学）；Shun Hing Institute of Advanced Engineering（信兴高等工程研究所）；National University of Singapore（新加坡国立大学）；NUSRI Suzhou（新加坡国立大学苏州研究院）；University College London（伦敦大学学院）；Wellcome/EPSRC Centre for Interventional and Surgical Sciences（维康/英国工程与自然科学研究委员会介入与外科科学中心）
Southern University of Science and Technology（南方科技大学）；The University of Hong Kong（香港大学）；Jiaxing Research Institute, Southern University of Science and Technology（南方科技大学嘉兴研究院）
Unsupervised domain adaptation has been proposed recently to tackle the so-called domain shift between training data and test data with different distributions. However, most of them only focus on single-target domain adaptation and cannot be applied to the scenario with multiple target domains. In this paper, we propose RVms, a novel unsupervised multi-target domain adaptation approach to segment retinal vessels (RVs) from multimodal and multicenter retinal images. RVms mainly consists of a style augmentation and transfer (SAT) module and a dual-teacher knowledge distillation (DTKD) module. S…
Fourier Test-time Adaptation with Multi-level Consistency for Robust Classification
Shenzhen University（深圳大学）；Zhejiang University（浙江大学）；University of Leeds（利兹大学）；Shenzhen RayShape Medical Technology Co., Ltd（深圳瑞影医疗科技有限公司）；Nanjing Medical University（南京医科大学）；The Affiliated Suzhou Hospital of Nanjing Medical University（南京医科大学附属苏州医院）
SAM-Based Building Change Detection with Distribution-Aware Fourier Adaptation and Edge-Constrained Warping
School of Information Science and Technology, Southwest Jiaotong University（西南交通大学信息科学与技术学院）；School of Computer Science, China University of Geosciences（中国地质大学计算机学院）；University of Extremadura（埃斯特雷马杜拉大学）
Tissue Segmentation of Thick-Slice Fetal Brain MR Scans with Guidance from High-Quality Isotropic Volumes
ShanghaiTech University（上海科技大学）；Fudan University（复旦大学）；Obstetrics and Gynecology Hospital of Fudan University（复旦大学附属妇产科医院）；Northwestern Polytechnical University（西北工业大学）；Shanghai United Imaging Intelligence company Ltd.（上海联影智能科技有限公司）；Shanghai Clinical Research and Trial Center（上海临床研究中心）
Integrating Frequency-Domain Representations with Low-Rank Adaptation in Vision-Language Models
University of Maryland Baltimore County (UMBC)（马里兰大学巴尔的摩县分校）；Center for Real-time Distributed Sensing and Autonomy (CARDS)（实时分布式感知与自主中心）；DEVCOM Army Research Laboratory（DEVCOM陆军研究实验室）
From Adaptation to Generalization: Adaptive Visual Prompting for Medical Image Segmentation
Technical University of Munich（慕尼黑技术大学）；Korea University（韩国大学）；Kyung Hee University（庆熙大学）；Seoul National University of Science and Technology（首尔科学技术大学）
In recent years, there has been tremendous progress in the field of semantic segmentation. However, one remaining challenging problem is that segmentation models do not generalize to unseen domains. To overcome this problem, one either has to label lots of data covering the whole variety of domains, which is often infeasible in practice, or apply unsupervised domain adaptation (UDA), only requiring labeled source data. In this work, we focus on UDA and additionally address the case of adapting not only to a single domain, but to a sequence of target domains. This requires mechanisms preventing…
FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning
School of Computer Science and Engineering, Southeast University, Nanjing, China（计算机科学与工程学院，东南大学，南京，中国）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用关键实验室（东南大学），教育部，中国）
Indian Institute of Science（印度科学学院）；Google Research（谷歌研究院）
Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting which considers a single labeled source domain against a compound of multi-modal unlabeled target data in order to generalize better on novel unseen domains. We hypothesize that an improved disentanglement of domain-related and task-related factors of dense intermediate layer features can greatly aid OCDA. Prior-arts attempt this indirectly by employing adversarial domain discriminators on the spatial CNN output. However, we find that latent features derived from the Fourier-based amplitude spectrum of deep CN…
In this work, we address the problem of unsupervised domain adaptation for person re-ID where annotations are available for the source domain but not for target. Previous methods typically follow a two-stage optimization pipeline, where the network is first pre-trained on source and then fine-tuned on target with pseudo labels created by feature clustering. Such methods sustain two main limitations. (1) The label noise may hinder the learning of discriminative features for recognizing target classes. (2) The domain gap may hinder knowledge transferring from source to target. We propose three t…
Anisotropic Fourier Features for Positional Encoding in Medical Imaging
Center of Digital Health, Berlin Institute of Health at Charité – Universitätsmedizin Berlin（柏林查理医院数字健康中心）；Charité – Universitätsmedizin Berlin（柏林查理医院大学医学中心）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）
