Unsupervised Domain Adaptation With Hierarchical Gradient Synchronization

2020-06-01 · CVPR 2020 6 · Lanqing Hu, Meina Kan, Shiguang Shan, Xilin Chen

Domain adaptation attempts to boost the performance on a target domain by borrowing knowledge from a well established source domain. To handle the distribution gap between two domains, the prominent approaches endeavor to extract domain-invariant features. It is known that after a perfect domain alignment the domain-invariant representations of two domains should share the same characteristics from perspective of the overview and also any local piece. Inspired by this, we propose a novel method called Hierarchical Gradient Synchronization to model the synchronization relationship among the local distribution pieces and global distribution, aiming for more precise domain-invariant features. Specifically, the hierarchical domain alignments including class-wise alignment, group-wise alignment and global alignment are first constructed. Then, these three types of alignment are constrained to be consistent to ensure better structure preservation. As a result, the obtained features are domain invariant and intrinsically structure preserved. As evaluated on extensive domain adaptation tasks, our proposed method achieves state-of-the-art classification performance on both vanilla unsupervised domain adaptation and partial domain adaptation.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Partial Domain Adaptation Unsupervised Domain Adaptation

Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction

2020-10-02 · Giovanni Bellitto, Federica Proietto Salanitri, Simone Palazzo, Francesco Rundo 외

In this work, we propose a 3D fully convolutional architecture for video saliency prediction that employs hierarchical supervision on intermediate maps (referred to as conspicuity maps) generated using features extracted…

Domain Adaptation Saliency Detection Saliency Prediction Unsupervised Domain Adaptation+2

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 Adaptation Unsupervised Domain Adaptation

Scaling Unsupervised Domain Adaptation through Optimal Collaborator Selection and Lazy Discriminator Synchronization

2021-01-01 · Akhil Mathur, Shaoduo Gan, Anton Isopoussu, Fahim Kawsar 외

Breakthroughs in unsupervised domain adaptation (uDA) have opened up the possibility of adapting models from a label-rich source domain to unlabeled target domains. Prior uDA works have primarily focused on improving ada…

Domain Adaptation Privacy Preserving Unsupervised Domain Adaptation

Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow

2023-03-24 · Hanyu Zhou, Yi Chang, Gang Chen, Luxin Yan

Optical flow estimation has made great progress, but usually suffers from degradation under adverse weather. Although semi/full-supervised methods have made good attempts, the domain shift between the synthetic and real …

Domain Adaptation Optical Flow Estimation

A Survey of Unsupervised Deep Domain Adaptation

2018-12-06 · Garrett Wilson, Diane J. Cook

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distributi…

Domain Adaptation Survey Transfer Learning Unsupervised Domain Adaptation