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

Iris presentation attack detection (PAD) has achieved remarkable success toensure the reliability and security of iris recognition systems. Most existingmethods exploit discriminative features in the spatial domain and reportoutstanding performance under intra-dataset settings. However, the degradationof performance is inevitable under cross-dataset settings, suffering fromdomain shift. In consideration of real-world applications, a small number ofbonafide samples are easily accessible. We thus define a new domain adaptationsetting called Few-shot One-class Domain Adaptation (FODA), where adaptationonly relies on a limited number of target bonafide samples. To address thisproblem, we propose a novel FODA framework based on the expressive power offrequency information. Specifically, our method integrates frequency-relatedinformation through two proposed modules. Frequency-based Attention Module(FAM) aggregates frequency information into spatial attention and explicitlyemphasizes high-frequency fine-grained features. Frequency Mixing Module (FMM)mixes certain frequency components to generate large-scale target-style samplesfor adaptation with limited target bonafide samples. Extensive experiments onLivDet-Iris 2017 dataset demonstrate the proposed method achievesstate-of-the-art or competitive performance under both cross-dataset andintra-dataset settings.

Few-shot One-class Domain Adaptation Based on Frequency for Iris Presentation Attack Detection