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

The class-agnostic counting (CAC) problem has caught increasing attentionrecently due to its wide societal applications and arduous challenges. To countobjects of different categories, existing approaches rely on user-providedexemplars, which is hard-to-obtain and limits their generality. In this paper,we aim to empower the framework to recognize adaptive exemplars within thewhole images. A zero-shot Generalized Counting Network (GCNet) is developed,which uses a pseudo-Siamese structure to automatically and effectively learnpseudo exemplar clues from inherent repetition patterns. In addition, aweakly-supervised scheme is presented to reduce the burden of laborious densitymaps required by all contemporary CAC models, allowing GCNet to be trainedusing count-level supervisory signals in an end-to-end manner. Withoutproviding any spatial location hints, GCNet is capable of adaptively capturingthem through a carefully-designed self-similarity learning strategy. Extensiveexperiments and ablation studies on the prevailing benchmark FSC147 forzero-shot CAC demonstrate the superiority of our GCNet. It performs on par withexisting exemplar-dependent methods and shows stunning cross-dataset generalityon crowd-specific datasets, e.g., ShanghaiTech Part A, Part B and UCF_QNRF.

GCNet: Probing Self-Similarity Learning for Generalized Counting Network