OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection
원문 초록
Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications. While zero-shot OOD detection, which requires no training on in-distribution (ID) data, has become feasible with the emergence of vision-language models like CLIP, existing methods primarily focus on semantic matching and fail to fully capture distributional discrepancies. To address these limitations, we propose OT-DETECTOR, a novel framework that employs Optimal Transport (OT) to quantify both semantic and distributional discrepancies between test samples and ID labels. Specifically, we introduce cross-modal transport mass and transport cost as semantic-wise and distribution-wise OOD scores, respectively, enabling more robust detection of OOD samples. Additionally, we present a semantic-aware content refinement (SaCR) module, which utilizes semantic cues from ID labels to amplify the distributional discrepancy between ID and hard OOD samples. Extensive experiments on several benchmarks demonstrate that OT-DETECTOR achieves state-of-the-art performance across various OOD detection tasks, particularly in challenging hard-OOD scenarios.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection
Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation
Kernel PCA for Out-of-Distribution Detection: Non-Linear Kernel Selections and Approximations
Unsupervised Out-of-Distribution Detection in Medical Imaging Using Multi-Exit Class Activation Maps and Feature Masking
Revisiting Likelihood-Based Out-of-Distribution Detection by Modeling Representations
Leveraging Perturbation Robustness to Enhance Out-of-Distribution Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.