Source-Free Domain Adaptation via Target Prediction Distribution Searching
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 wh...
Saved in:
Published in | International journal of computer vision Vol. 132; no. 3; pp. 654 - 672 |
---|---|
Main Authors | , , , , , |
Format | Journal Article |
Language | English |
Published |
New York
Springer US
01.03.2024
Springer Nature B.V |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | 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
. |
---|---|
ISSN: | 0920-5691 1573-1405 |
DOI: | 10.1007/s11263-023-01892-w |