English
Related papers

Related papers: Optimal Latent Vector Alignment for Unsupervised D…

200 papers

Optimal Transport (OT) has proven effective for domain adaptation (DA) by aligning distributions across domains with differing statistical properties. Building on the approach of Courty et al. (2016), who mapped source data to the target…

Machine Learning · Statistics 2025-05-15 Brian Britos , Mathias Bourel

The fine-grained localization of clinicians in the operating room (OR) is a key component to design the new generation of OR support systems. Computer vision models for person pixel-based segmentation and body-keypoints detection are needed…

Computer Vision and Pattern Recognition · Computer Science 2022-07-01 Vinkle Srivastav , Afshin Gangi , Nicolas Padoy

We present a semi-supervised domain adaptation framework for brain vessel segmentation from different image modalities. Existing state-of-the-art methods focus on a single modality, despite the wide range of available cerebrovascular…

Image and Video Processing · Electrical Eng. & Systems 2024-03-28 Francesco Galati , Daniele Falcetta , Rosa Cortese , Barbara Casolla , Ferran Prados , Ninon Burgos , Maria A. Zuluaga

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we introduce a novel approach called class-aware optimal transport (OT), which measures the OT…

Machine Learning · Computer Science 2024-01-30 Tuan Nguyen , Van Nguyen , Trung Le , He Zhao , Quan Hung Tran , Dinh Phung

Machine learning applications on signals such as computer vision or biomedical data often face significant challenges due to the variability that exists across hardware devices or session recordings. This variability poses a Domain…

Machine Learning · Computer Science 2024-07-22 Théo Gnassounou , Antoine Collas , Rémi Flamary , Karim Lounici , Alexandre Gramfort

Although unsupervised domain adaptation (UDA) is a promising direction to alleviate domain shift, they fall short of their supervised counterparts. In this work, we investigate relatively less explored semi-supervised domain adaptation…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Hritam Basak , Zhaozheng Yin

Unsupervised domain adaptation (UDA) methods have shown their promising performance in the cross-modality medical image segmentation tasks. These typical methods usually utilize a translation network to transform images from the source…

Image and Video Processing · Electrical Eng. & Systems 2021-01-19 Xiaoting Han , Lei Qi , Qian Yu , Ziqi Zhou , Yefeng Zheng , Yinghuan Shi , Yang Gao

With the widespread success of deep learning in biomedical image segmentation, domain shift becomes a critical and challenging problem, as the gap between two domains can severely affect model performance when deployed to unseen data with…

Computer Vision and Pattern Recognition · Computer Science 2021-03-04 Ping Gong , Wenwen Yu , Qiuwen Sun , Ruohan Zhao , Junfeng Hu

Shape information is a strong and valuable prior in segmenting organs in medical images. However, most current deep learning based segmentation algorithms have not taken shape information into consideration, which can lead to bias towards…

Computer Vision and Pattern Recognition · Computer Science 2022-07-07 Yuan Yao , Fengze Liu , Zongwei Zhou , Yan Wang , Wei Shen , Alan Yuille , Yongyi Lu

This paper proposes a novel approach for unsupervised domain adaptation (UDA) with target shift. Target shift is a problem of mismatch in label distribution between source and target domains. Typically it appears as class-imbalance in…

Computer Vision and Pattern Recognition · Computer Science 2020-01-28 Ryuhei Takahashi , Atsushi Hashimoto , Motoharu Sonogashira , Masaaki Iiyama

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…

Computer Vision and Pattern Recognition · Computer Science 2022-07-06 Jogendra Nath Kundu , Akshay Kulkarni , Suvaansh Bhambri , Varun Jampani , R. Venkatesh Babu

Deep neural networks (DNNs) have been widely used for medical image analysis. However, the lack of access a to large-scale annotated dataset poses a great challenge, especially in the case of rare diseases, or new domains for the research…

Image and Video Processing · Electrical Eng. & Systems 2021-07-02 Sungho Suh , Sojeong Cheon , Wonseo Choi , Yeon Woong Chung , Won-Kyung Cho , Ji-Sun Paik , Sung Eun Kim , Dong-Jin Chang , Yong Oh Lee

Domain shift presents a significant challenge in applying Deep Learning to the segmentation of 3D medical images from sources like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT). Although numerous Domain Adaptation methods…

Image and Video Processing · Electrical Eng. & Systems 2025-02-25 Boris Shirokikh , Anvar Kurmukov , Mariia Donskova , Valentin Samokhin , Mikhail Belyaev , Ivan Oseledets

The recent prevalence of deep neural networks has lead semantic segmentation networks to achieve human-level performance in the medical field when sufficient training data is provided. Such networks however fail to generalize when tasked…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Serban Stan , Mohammad Rostami

A deep learning model trained on some labeled data from a certain source domain generally performs poorly on data from different target domains due to domain shifts. Unsupervised domain adaptation methods address this problem by alleviating…

Image and Video Processing · Electrical Eng. & Systems 2019-08-30 Junlin Yang , Nicha C. Dvornek , Fan Zhang , Julius Chapiro , MingDe Lin , James S. Duncan

In an effort to reduce annotation costs in action recognition, unsupervised video domain adaptation methods have been proposed that aim to adapt a predictive model from a labelled dataset (i.e., source domain) to an unlabelled dataset…

Computer Vision and Pattern Recognition · Computer Science 2023-01-10 Giacomo Zara , Victor Guilherme Turrisi da Costa , Subhankar Roy , Paolo Rota , Elisa Ricci

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…

Computer Vision and Pattern Recognition · Computer Science 2022-08-05 Alvaro Gomariz , Huanxiang Lu , Yun Yvonna Li , Thomas Albrecht , Andreas Maunz , Fethallah Benmansour , Alessandra M. Valcarcel , Jennifer Luu , Daniela Ferrara , Orcun Goksel

Manual annotation of 3D medical images for segmentation tasks is tedious and time-consuming. Moreover, data privacy limits the applicability of crowd sourcing to perform data annotation in medical domains. As a result, training deep neural…

Computer Vision and Pattern Recognition · Computer Science 2024-10-15 Ruitong Sun , Mohammad Rostami

Optical coherence tomography (OCT) imaging from different camera devices causes challenging domain shifts and can cause a severe drop in accuracy for machine learning models. In this work, we introduce a minimal noise adaptation method…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Valentin Koch , Olle Holmberg , Hannah Spitzer , Johannes Schiefelbein , Ben Asani , Michael Hafner , Fabian J Theis

Convolutional neural networks (CNNs) have led to significant improvements in the semantic segmentation of images. When source and target datasets come from different modalities, CNN performance suffers due to domain shift. In such cases…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Serban Stan , Mohammad Rostami