paper-with-me

홈 › Papers

OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation

2022-05-22 · Thanh-Dat Truong, Naga Venkata Sai Raviteja Chappa, Xuan Bac Nguyen, Ngan Le, Ashley Dowling, Khoa Luu

Unsupervised domain adaptation is one of the challenging problems in computer vision. This paper presents a novel approach to unsupervised domain adaptations based on the optimal transport-based distance. Our approach allows aligning target and source domains without the requirement of meaningful metrics across domains. In addition, the proposal can associate the correct mapping between source and target domains and guarantee a constraint of topology between source and target domains. The proposed method is evaluated on different datasets in various problems, i.e. (i) digit recognition on MNIST, MNIST-M, USPS datasets, (ii) Object recognition on Amazon, Webcam, DSLR, and VisDA datasets, (iii) Insect Recognition on the IP102 dataset. The experimental results show that our proposed method consistently improves performance accuracy. Also, our framework could be incorporated with any other CNN frameworks within an end-to-end deep network design for recognition problems to improve their performance.

📄 PDF Abstract BibTeX arXiv:2205.10738

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationObject RecognitionUnsupervised Domain Adaptation

Similar Papers 제목 키워드 기반

Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation

2020-06-01 · CVPR 2020 6 · Renjun Xu, Pelen Liu, Liyan Wang, Chao Chen 외

Recently, extensive researches have been proposed to address the UDA problem, which aims to learn transferrable models for the unlabeled target domain. Among them, the optimal transport is a promising metric to align the…

ClusteringDomain AdaptationUnsupervised Domain Adaptation

Hierarchical Optimal Transport for Unsupervised Domain Adaptation

2021-12-03 · Mourad El Hamri, Younès Bennani, Issam Falih, Hamid Ahaggach

In this paper, we propose a novel approach for unsupervised domain adaptation, that relates notions of optimal transport, learning probability measures and unsupervised learning. The proposed approach, HOT-DA, is based o…

Domain AdaptationUnsupervised Domain Adaptation

Feature Selection for Unsupervised Domain Adaptation using Optimal Transport

2018-06-28 · Léo Gautheron, Ievgen Redko, Carole Lartizien

In this paper, we propose a new feature selection method for unsupervised domain adaptation based on the emerging optimal transportation theory. We build upon a recent theoretical analysis of optimal transport in domain …

Domain Adaptationfeature selectionUnsupervised Domain Adaptation

Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport

2021-11-11 · NeurIPS 2021 12 · Hsin-Yi Lin, Huan-Hsin Tseng, Xugang Lu, Yu Tsao

This paper presents a novel discriminator-constrained optimal transport network (DOTN) that performs unsupervised domain adaptation for speech enhancement (SE), which is an essential regression task in speech processing.…

Domain AdaptationSpeech EnhancementUnsupervised Domain Adaptation

Margin-aware Adversarial Domain Adaptation with Optimal Transport

2020-01-01 · ICML 2020 1 · Sofien Dhouib, Ievgen Redko, Carole Lartizien

In this paper, we propose a new theoretical analysis of unsupervised domain adaptation that relates notions of large margin separation, adversarial learning and optimal transport. This analysis generalizes previous work …

Domain AdaptationUnsupervised Domain Adaptation