RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations
- URL: http://arxiv.org/abs/2503.22285v1
- Date: Fri, 28 Mar 2025 10:01:55 GMT
- Title: RUNA: Object-level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations
- Authors: Bin Zhang, Jinggang Chen, Xiaoyang Qu, Guokuan Li, Kai Lu, Jiguang Wan, Jing Xiao, Jianzong Wang,
- Abstract summary: RUNA is a novel framework for detecting out-of-distribution (OOD) objects.<n>It employs a regional uncertainty alignment mechanism to distinguish ID from OOD objects effectively.<n>Our experiments show that RUNA substantially surpasses state-of-the-art methods in object-level OOD detection.
- Score: 33.971901643313856
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection [22.200900846112805]
We introduce a new method to adapt CLIP for zero-shot object-level OOD detection.<n>Our method preserves critical contextual information and improves the ability to differentiate between ID and OOD objects.
arXiv Detail & Related papers (2025-03-28T10:08:17Z) - Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection [71.93411099797308]
Out-of-distribution (OOD) samples are crucial when deploying machine learning models in open-world scenarios.
We propose to tackle this constraint by leveraging the expert knowledge and reasoning capability of large language models (LLM) to potential Outlier Exposure, termed EOE.
EOE can be generalized to different tasks, including far, near, and fine-language OOD detection.
EOE achieves state-of-the-art performance across different OOD tasks and can be effectively scaled to the ImageNet-1K dataset.
arXiv Detail & Related papers (2024-06-02T17:09:48Z) - Detecting Out-of-Distribution Through the Lens of Neural Collapse [7.04686607977352]
Out-of-Distribution (OOD) detection is critical for safe deployment.
Inspired by the phenomenon of Neural Collapse, we propose a versatile and efficient OOD detection method.
arXiv Detail & Related papers (2023-11-02T05:18:28Z) - Exploring Large Language Models for Multi-Modal Out-of-Distribution
Detection [67.68030805755679]
Large language models (LLMs) encode a wealth of world knowledge and can be prompted to generate descriptive features for each class.
In this paper, we propose to apply world knowledge to enhance OOD detection performance through selective generation from LLMs.
arXiv Detail & Related papers (2023-10-12T04:14:28Z) - From Global to Local: Multi-scale Out-of-distribution Detection [129.37607313927458]
Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process.
Recent progress in representation learning gives rise to distance-based OOD detection.
We propose Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details.
arXiv Detail & Related papers (2023-08-20T11:56:25Z) - Detecting Out-of-distribution Objects Using Neuron Activation Patterns [0.0]
We introduce Neuron Activation PaTteRns for out-of-distribution samples detection in Object detectioN (NAPTRON)
Our approach outperforms state-of-the-art methods, without the need to affect in-distribution (ID) performance.
We have created the largest open-source benchmark for OOD object detection.
arXiv Detail & Related papers (2023-07-31T06:41:26Z) - General-Purpose Multi-Modal OOD Detection Framework [5.287829685181842]
Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems.
We propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component.
We evaluate the proposed WOOD model on multiple real-world datasets, and the experimental results demonstrate that the WOOD model outperforms the state-of-the-art methods for multi-modal OOD detection.
arXiv Detail & Related papers (2023-07-24T18:50:49Z) - Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts [91.43701971416213]
We introduce a context-aware OOD intent detection (Caro) framework to model multi-turn contexts in OOD intent detection tasks.
Caro establishes state-of-the-art performances on multi-turn OOD detection tasks by improving the F1-OOD score of over $29%$ compared to the previous best method.
arXiv Detail & Related papers (2023-05-05T01:39:21Z) - Improving Out-of-Distribution Detection with Disentangled Foreground and Background Features [23.266183020469065]
We propose a novel framework that disentangles foreground and background features from ID training samples via a dense prediction approach.
It is a generic framework that allows for a seamless combination with various existing OOD detection methods.
arXiv Detail & Related papers (2023-03-15T16:12:14Z) - YolOOD: Utilizing Object Detection Concepts for Multi-Label
Out-of-Distribution Detection [25.68925703896601]
YolOOD is a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task.
We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.
arXiv Detail & Related papers (2022-12-05T07:52:08Z) - Pseudo-OOD training for robust language models [78.15712542481859]
OOD detection is a key component of a reliable machine-learning model for any industry-scale application.
We propose POORE - POsthoc pseudo-Ood REgularization, that generates pseudo-OOD samples using in-distribution (IND) data.
We extensively evaluate our framework on three real-world dialogue systems, achieving new state-of-the-art in OOD detection.
arXiv Detail & Related papers (2022-10-17T14:32:02Z) - Triggering Failures: Out-Of-Distribution detection by learning from
local adversarial attacks in Semantic Segmentation [76.2621758731288]
We tackle the detection of out-of-distribution (OOD) objects in semantic segmentation.
Our main contribution is a new OOD detection architecture called ObsNet associated with a dedicated training scheme based on Local Adversarial Attacks (LAA)
We show it obtains top performances both in speed and accuracy when compared to ten recent methods of the literature on three different datasets.
arXiv Detail & Related papers (2021-08-03T17:09:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.