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

Open-set object detection (OSOD) has recently gained attention. It is todetect unknown objects while correctly detecting known objects. In this paper,we first point out that the recent studies' formalization of OSOD, whichgeneralizes open-set recognition (OSR) and thus considers an unlimited varietyof unknown objects, has a fundamental issue. This issue emerges from thedifference between image classification and object detection, making it hard toevaluate OSOD methods' performance properly. We then introduce a novel scenarioof OSOD, which considers known and unknown classes within a specifiedsuper-class of object classes. This new scenario has practical applications andis free from the above issue, enabling proper evaluation of OSOD performanceand probably making the problem more manageable. Finally, we experimentallyevaluate existing OSOD methods with the new scenario using multiple datasets,showing that the current state-of-the-art OSOD methods attain limitedperformance similar to a simple baseline method. The paper also presents ataxonomy of OSOD that clarifies different problem formalizations. We hope ourstudy helps the community reconsider OSOD problems and progress in the rightdirection.

Rectifying Open-set Object Detection: A Taxonomy, Practical Applications, and Proper Evaluation