Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Zongjian, Zhang, Lei
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2605.25706
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914599396179968
author Wu, Zongjian
Zhang, Lei
author_facet Wu, Zongjian
Zhang, Lei
contents Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in vision-language models have led to substantial improvements in REC tasks, current REC benchmarks often hold simple scenarios and the assumption that each expression maps to a unique object. These limitations hinder the deployment of REC models in open-world environments. To fill this gap, we introduce OpenRef, a new benchmark for REC in complex visual and linguistic scenarios. OpenRef features three key advancements: 1) Diverse visual scenarios: spanning diverse visual domains, including ground views, drone views, dark scenes and adverse weather conditions; 2) Variable target counts: breaking the single-target limitation with multi-target and none-target samples; 3) Rich vocabulary types: incorporating proper nouns, polysemous words and ordinal terms to fit a wider range of expression needs. Furthermore, as traditional metrics are insufficient for open-world setting, we leverage F1 to measure grounding accuracy and propose N3R (Negative Relative Rejection Reliability) to assess relative rejection reliability against negative expressions. Finally, we introduce Multi-task Consistency Checker (MCC), a training-free but plug-and-play strategy that enhances model performance with one click by enforcing consistency self-verification. Extensive experiments demonstrate that this work significantly advances the performance of existing REC models in complex scenarios, paving the way for open-world REC. Project page: https://zongjianwu.github.io/openref
format Preprint
id arxiv_https___arxiv_org_abs_2605_25706
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker
Wu, Zongjian
Zhang, Lei
Computer Vision and Pattern Recognition
Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in vision-language models have led to substantial improvements in REC tasks, current REC benchmarks often hold simple scenarios and the assumption that each expression maps to a unique object. These limitations hinder the deployment of REC models in open-world environments. To fill this gap, we introduce OpenRef, a new benchmark for REC in complex visual and linguistic scenarios. OpenRef features three key advancements: 1) Diverse visual scenarios: spanning diverse visual domains, including ground views, drone views, dark scenes and adverse weather conditions; 2) Variable target counts: breaking the single-target limitation with multi-target and none-target samples; 3) Rich vocabulary types: incorporating proper nouns, polysemous words and ordinal terms to fit a wider range of expression needs. Furthermore, as traditional metrics are insufficient for open-world setting, we leverage F1 to measure grounding accuracy and propose N3R (Negative Relative Rejection Reliability) to assess relative rejection reliability against negative expressions. Finally, we introduce Multi-task Consistency Checker (MCC), a training-free but plug-and-play strategy that enhances model performance with one click by enforcing consistency self-verification. Extensive experiments demonstrate that this work significantly advances the performance of existing REC models in complex scenarios, paving the way for open-world REC. Project page: https://zongjianwu.github.io/openref
title Towards Open-World Referring Expression Comprehension: A Benchmark with Training-free Multi-task Consistency Checker
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.25706