Visual Domain Adaptation Exploiting Confidence-Samples

Tang, Song; Ji, Yao; Lyu, Jianzhi; Mi, Jinpeng; Li, Qingdu; Zhang, Jianwei

doi:10.1109/iros40897.2019.8967714

Cited by 4 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[23] perform the transfer via manifold embedded distribution alignment. [24] develop an energy distribution-based classifier by which the confidence target data are detected. In all the aforementioned methods, the source data is indispensable because the labeled samples are used to formulate domain knowledge explicitly (e.g., probability, geometrical structure, or energy).…”

Section: A Unsupervised Domain Adaptationmentioning

confidence: 99%

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

Tang,

Yang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In the classic setting of unsupervised domain adaptation (UDA), the labeled source data are available in the training phase. However, in many real-world scenarios, owing to some reasons such as privacy protection and information security, the source data is inaccessible, and only a model trained on the source domain is available. This paper proposes a novel deep clustering method for this challenging task. Aiming at the dynamical clustering at feature-level, we introduce extra constraints hidden in the geometric structure between data to assist the process. Concretely, we propose a geometry-based constraint, named semantic consistency on the nearest neighborhood (SCNNH), and use it to encourage robust clustering. To reach this goal, we construct the nearest neighborhood for every target data and take it as the fundamental clustering unit by building our objective on the geometry. Also, we develop a more SCNNH-compliant structure with an additional semantic credibility constraint, named semantic hyper-nearest neighborhood (SHNNH). After that, we extend our method to this new geometry. Extensive experiments on three challenging UDA datasets indicate that our

show abstract

Section: A Unsupervised Domain Adaptationmentioning

confidence: 99%

Nearest Neighborhood-Based Deep Clustering for Source Data-absent Unsupervised Domain Adaptation

Tang,

Yang,

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Source-Free Domain Adaptation via Target Prediction Distribution Searching

Tang,

Chang,

Zhang

et al. 2023

Int J Comput Vis

View full text Add to dashboard Cite

Existing Source-Free Domain Adaptation (SFDA) methods typically adopt the feature distribution alignment paradigm via mining auxiliary information (eg., pseudo-labelling, source domain data generation). However, they are largely limited due to that the auxiliary information is usually error-prone whilst lacking effective error-mitigation mechanisms. To overcome this fundamental limitation, in this paper we propose a novel Target Prediction Distribution Searching (TPDS) paradigm. Theoretically, we prove that in case of sufficient small distribution shift, the domain transfer error could be well bounded. To satisfy this condition, we introduce a flow of proxy distributions that facilitates the bridging of typically large distribution shift from the source domain to the target domain. This results in a progressive searching on the geodesic path where adjacent proxy distributions are regularized to have small shift so that the overall errors can be minimized. To account for the sequential correlation between proxy distributions, we develop a new pairwise alignment with category consistency algorithm for minimizing the adaptation errors. Specifically, a manifold geometry guided cross-distribution neighbour search is designed to detect the data pairs supporting the Wasserstein distance based shift measurement. Mutual information maximization is then adopted over these pairs for shift regularization. Extensive experiments on five challenging SFDA benchmarks show that our TPDS achieves new state-of-the-art performance. The code and datasets are available at https://github.com/tntek/TPDS.

show abstract