Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation

2017-02-21 · Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò

The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains. Alleviating the domain shift problem, especially in the challenging setting where no labeled data are available for the target domain, is paramount for having visual recognition systems working in the wild. As the problem stems from a shift among distributions, intuitively one should try to align them. In the literature, this has resulted in a stream of works attempting to align the feature representations learned from the source and target domains. Here we take a different route. Rather than introducing regularization terms aiming to promote the alignment of the two representations, we act at the distribution level through the introduction of \emph{DomaIn Alignment Layers} (\DIAL), able to match the observed source and target data distributions to a reference one. Thorough experiments on three different public benchmarks we confirm the power of our approach.

📄 PDF Abstract BibTeX arXiv:1702.06332

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Unsupervised Domain Adaptation

AutoDIAL: Automatic DomaIn Alignment Layers

2017-04-26 · ICCV 2017 10 · Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci 외

Classifiers trained on given databases perform poorly when tested on data acquired in different settings. This is explained in domain adaptation through a shift among distributions of the source and target domains. Attem…

Domain Adaptation

Improving Transferability of Domain Adaptation Networks Through Domain Alignment Layers

2021-09-06 · Lucas Fernando Alvarenga e Silva, Daniel Carlos Guimarães Pedronette, Fábio Augusto Faria, João Paulo Papa 외

Deep learning (DL) has been the primary approach used in various computer vision tasks due to its relevant results achieved on many tasks. However, on real-world scenarios with partially or no labeled data, DL methods ar…

Domain Adaptation Multi-Source Unsupervised Domain Adaptation Unsupervised Domain Adaptation

Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation

2022-02-27 · Xu Ma, Junkun Yuan, Yen-Wei Chen, Ruofeng Tong 외

Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To bridge the gap between source and target domains, one pr…

Domain Adaptation Semantic Similarity Semantic Textual Similarity Unsupervised Domain Adaptation

Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization

2018-01-30 · ECCV 2018 9 · Guoliang Kang, Liang Zheng, Yan Yan, Yi Yang

In this paper, we make two contributions to unsupervised domain adaptation (UDA) using the convolutional neural network (CNN). First, our approach transfers knowledge in all the convolutional layers through attention ali…

Domain Adaptation Unsupervised Domain Adaptation

Bi-Dimensional Feature Alignment for Cross-Domain Object Detection

2020-11-14 · Zhen Zhao, Yuhong Guo, Jieping Ye

Recently the problem of cross-domain object detection has started drawing attention in the computer vision community. In this paper, we propose a novel unsupervised cross-domain detection model that exploits the annotate…

Object Object Detection Unsupervised Domain Adaptation