RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Bin, Chen, Jinggang, Qu, Xiaoyang, Li, Guokuan, Lu, Kai, Wan, Jiguang, Xiao, Jing, Wang, Jianzong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908288434569216
author Zhang, Bin
Chen, Jinggang
Qu, Xiaoyang
Li, Guokuan
Lu, Kai
Wan, Jiguang
Xiao, Jing
Wang, Jianzong
author_facet Zhang, Bin
Chen, Jinggang
Qu, Xiaoyang
Li, Guokuan
Lu, Kai
Wan, Jiguang
Xiao, Jing
Wang, Jianzong
contents Enabling object detectors to recognize out-of-distribution (OOD) objects is vital for building reliable systems. A primary obstacle stems from the fact that models frequently do not receive supervisory signals from unfamiliar data, leading to overly confident predictions regarding OOD objects. Despite previous progress that estimates OOD uncertainty based on the detection model and in-distribution (ID) samples, we explore using pre-trained vision-language representations for object-level OOD detection. We first discuss the limitations of applying image-level CLIP-based OOD detection methods to object-level scenarios. Building upon these insights, we propose RUNA, a novel framework that leverages a dual encoder architecture to capture rich contextual information and employs a regional uncertainty alignment mechanism to distinguish ID from OOD objects effectively. We introduce a few-shot fine-tuning approach that aligns region-level semantic representations to further improve the model's capability to discriminate between similar objects. Our experiments show that RUNA substantially surpasses state-of-the-art methods in object-level OOD detection, particularly in challenging scenarios with diverse and complex object instances.
format Preprint
id arxiv_https___arxiv_org_abs_2503_22285
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations
Zhang, Bin
Chen, Jinggang
Qu, Xiaoyang
Li, Guokuan
Lu, Kai
Wan, Jiguang
Xiao, Jing
Wang, Jianzong
Computer Vision and Pattern Recognition
Enabling object detectors to recognize out-of-distribution (OOD) objects is vital for building reliable systems. A primary obstacle stems from the fact that models frequently do not receive supervisory signals from unfamiliar data, leading to overly confident predictions regarding OOD objects. Despite previous progress that estimates OOD uncertainty based on the detection model and in-distribution (ID) samples, we explore using pre-trained vision-language representations for object-level OOD detection. We first discuss the limitations of applying image-level CLIP-based OOD detection methods to object-level scenarios. Building upon these insights, we propose RUNA, a novel framework that leverages a dual encoder architecture to capture rich contextual information and employs a regional uncertainty alignment mechanism to distinguish ID from OOD objects effectively. We introduce a few-shot fine-tuning approach that aligns region-level semantic representations to further improve the model's capability to discriminate between similar objects. Our experiments show that RUNA substantially surpasses state-of-the-art methods in object-level OOD detection, particularly in challenging scenarios with diverse and complex object instances.
title RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.22285