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

Heterogeneous Face Recognition (HFR) refers to matching face images capturedin different domains, such as thermal to visible images (VIS), sketches tovisible images, near-infrared to visible, and so on. This is particularlyuseful in matching visible spectrum images to images captured from othermodalities. Though highly useful, HFR is challenging because of the domain gapbetween the source and target domain. Often, large-scale paired heterogeneousface image datasets are absent, preventing training models specifically for theheterogeneous task. In this work, we propose a surprisingly simple, yet, veryeffective method for matching face images across different sensing modalities.The core idea of the proposed approach is to add a novel neural network blockcalled Prepended Domain Transformer (PDT) in front of a pre-trained facerecognition (FR) model to address the domain gap. Retraining this new blockwith few paired samples in a contrastive learning setup was enough to achievestate-of-the-art performance in many HFR benchmarks. The PDT blocks can beretrained for several source-target combinations using the proposed generalframework. The proposed approach is architecture agnostic, meaning they can beadded to any pre-trained FR models. Further, the approach is modular and thenew block can be trained with a minimal set of paired samples, making it mucheasier for practical deployment. The source code and protocols will be madeavailable publicly.

Prepended Domain Transformer: Heterogeneous Face Recognition without Bells and Whistles