# Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation

Source: [Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation](<https://www.sota2.com/research/paper/68fa75d41e209131cea6a154>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:11.277Z

Authors: Jinwoo Ahn, Hyeokjoon Kwon, Hwiyeon Yoo

Published: 2024-11-23T18:13:27.000Z

## Abstract

Recent advent of vision-based foundation models has enabled efficient and high-quality object detection at ease. Despite the success of previous studies, object detection models face limitations on capturing small components from holistic objects and taking user intention into account. To address these challenges, we propose a novel foundation model-based detection method called FOCUS: Fine-grained Open-Vocabulary Object ReCognition via User-Guided Segmentation. FOCUS merges the capabilities of vision foundation models to automate open-vocabulary object detection at flexible granularity and allow users to directly guide the detection process via natural language. It not only excels at identifying and locating granular constituent elements but also minimizes unnecessary user intervention yet grants them significant control. With FOCUS, users can make explainable requests to actively guide the detection process in the intended direction. Our results show that FOCUS effectively enhances the detection capabilities of baseline models and shows consistent performance across varying object types.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2411.15620>)

[PDF](<https://arxiv.org/pdf/2411.15620.pdf>)
