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

Modern two-stage object detectors generally require excessively large modelsfor their detection heads to achieve high accuracy. To address this problem, wepropose that the model parameters of two-stage detection heads can be condensedand reduced by concentrating on object key parts. To this end, we firstintroduce an automatic object key part discovery task to make neural networksdiscover representative sub-parts in each foreground object. With thesediscovered key parts, we then decompose the object appearance modeling into akey part modeling process and a global modeling process for detection. Key partmodeling encodes fine and detailed features from the discovered key parts, andglobal modeling encodes rough and holistic object characteristics. In practice,such decomposition allows us to significantly abridge model parameters withoutsacrificing much detection accuracy. Experiments on popular datasets illustratethat our proposed technique consistently maintains original performance whilewaiving around 50% of the model parameters of common two-stage detection heads,with the performance only deteriorating by 1.5% when waiving around 96% of theoriginal model parameters. Codes are released on:https://github.com/zhechen/Condensing2stageDetection.

Condensing Two-stage Detection with Automatic Object Key Part Discovery