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

Recent advancements in large vision-language models enabled visual objectdetection in open-vocabulary scenarios, where object classes are defined infree-text formats during inference. In this paper, we aim to probe thestate-of-the-art methods for open-vocabulary object detection to determine towhat extent they understand fine-grained properties of objects and their parts.To this end, we introduce an evaluation protocol based on dynamic vocabularygeneration to test whether models detect, discern, and assign the correctfine-grained description to objects in the presence of hard-negative classes.We contribute with a benchmark suite of increasing difficulty and probingdifferent properties like color, pattern, and material. We further enhance ourinvestigation by evaluating several state-of-the-art open-vocabulary objectdetectors using the proposed protocol and find that most existing solutions,which shine in standard open-vocabulary benchmarks, struggle to accuratelycapture and distinguish finer object details. We conclude the paper byhighlighting the limitations of current methodologies and exploring promisingresearch directions to overcome the discovered drawbacks. Data and code areavailable at https://github.com/lorebianchi98/FG-OVD.

The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding