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

Unsupervised domain adaptation (UDA) methods facilitate the transfer ofmodels to target domains without labels. However, these methods necessitate alabeled target validation set for hyper-parameter tuning and model selection.In this paper, we aim to find an evaluation metric capable of assessing thequality of a transferred model without access to target validation labels. Webegin with the metric based on mutual information of the model prediction.Through empirical analysis, we identify three prevalent issues with thismetric: 1) It does not account for the source structure. 2) It can be easilyattacked. 3) It fails to detect negative transfer caused by the over-alignmentof source and target features. To address the first two issues, we incorporatesource accuracy into the metric and employ a new MLP classifier that is heldout during training, significantly improving the result. To tackle the finalissue, we integrate this enhanced metric with data augmentation, resulting in anovel unsupervised UDA metric called the Augmentation Consistency Metric (ACM).Additionally, we empirically demonstrate the shortcomings of previousexperiment settings and conduct large-scale experiments to validate theeffectiveness of our proposed metric. Furthermore, we employ our metric toautomatically search for the optimal hyper-parameter set, achieving superiorperformance compared to manually tuned sets across four common benchmarks.Codes will be available soon.

A Study of Unsupervised Evaluation Metrics for Practical and Automatic Domain Adaptation