Saved in:
Bibliographic Details
Main Authors: Li, Xiang, Qiu, Kai, Wang, Jinglu, Xu, Xiaohao, Singh, Rita, Yamazak, Kashu, Chen, Hao, Huang, Xiaonan, Raj, Bhiksha
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.04924
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917608213708800
author Li, Xiang
Qiu, Kai
Wang, Jinglu
Xu, Xiaohao
Singh, Rita
Yamazak, Kashu
Chen, Hao
Huang, Xiaonan
Raj, Bhiksha
author_facet Li, Xiang
Qiu, Kai
Wang, Jinglu
Xu, Xiaohao
Singh, Rita
Yamazak, Kashu
Chen, Hao
Huang, Xiaonan
Raj, Bhiksha
contents Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite progress in this field, the robustness of referring perception models (RPMs) against disruptive perturbations is not well explored. This work thoroughly assesses the resilience of RPMs against various perturbations in both general and specific contexts. Recognizing the complex nature of referring perception tasks, we present a comprehensive taxonomy of perturbations, and then develop a versatile toolbox for synthesizing and evaluating the effects of composite disturbances. Employing this toolbox, we construct $\text{R}^2$-Bench, a benchmark for assessing the Robustness of Referring perception models under noisy conditions across five key tasks. Moreover, we propose the $\text{R}^2$-Agent, an LLM-based agent that simplifies and automates model evaluation via natural language instructions. Our investigation uncovers the vulnerabilities of current RPMs to various perturbations and provides tools for assessing model robustness, potentially promoting the safe and resilient integration of intelligent systems into complex real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2403_04924
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle $\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
Li, Xiang
Qiu, Kai
Wang, Jinglu
Xu, Xiaohao
Singh, Rita
Yamazak, Kashu
Chen, Hao
Huang, Xiaonan
Raj, Bhiksha
Computer Vision and Pattern Recognition
Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite progress in this field, the robustness of referring perception models (RPMs) against disruptive perturbations is not well explored. This work thoroughly assesses the resilience of RPMs against various perturbations in both general and specific contexts. Recognizing the complex nature of referring perception tasks, we present a comprehensive taxonomy of perturbations, and then develop a versatile toolbox for synthesizing and evaluating the effects of composite disturbances. Employing this toolbox, we construct $\text{R}^2$-Bench, a benchmark for assessing the Robustness of Referring perception models under noisy conditions across five key tasks. Moreover, we propose the $\text{R}^2$-Agent, an LLM-based agent that simplifies and automates model evaluation via natural language instructions. Our investigation uncovers the vulnerabilities of current RPMs to various perturbations and provides tools for assessing model robustness, potentially promoting the safe and resilient integration of intelligent systems into complex real-world scenarios.
title $\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.04924