English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Standard Unsupervised Domain Adaptation (UDA) methods assume the availabilityof both source and target data during the adaptation. In this work, weinvestigate Source-free Unsupervised Domain Adaptation (SF-UDA), a specificcase of UDA where a model is adapted to a target domain without access tosource data. We propose a novel approach for the SF-UDA setting based on a lossreweighting strategy that brings robustness against the noise that inevitablyaffects the pseudo-labels. The classification loss is reweighted based on thereliability of the pseudo-labels that is measured by estimating theiruncertainty. Guided by such reweighting strategy, the pseudo-labels areprogressively refined by aggregating knowledge from neighbouring samples.Furthermore, a self-supervised contrastive framework is leveraged as a targetspace regulariser to enhance such knowledge aggregation. A novel negative pairsexclusion strategy is proposed to identify and exclude negative pairs made ofsamples sharing the same class, even in presence of some noise in thepseudo-labels. Our method outperforms previous methods on three majorbenchmarks by a large margin. We set the new SF-UDA state-of-the-art on VisDA-Cand DomainNet with a performance gain of +1.8% on both benchmarks and on PACSwith +12.3% in the single-source setting and +6.6% in multi-target adaptation.Additional analyses demonstrate that the proposed approach is robust to thenoise, which results in significantly more accurate pseudo-labels compared tostate-of-the-art approaches.

Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptation