Enhancing Out-of-Distribution Detection in Transfer Learning Through Intuitionistic Fuzzy Set-Based Prediction

Guangzhi Ma, Jie Lu

Abstract: Out-of-distribution (OOD) detection involves training a model on in-distribution (ID) samples to determine whether a given input belongs to classes that were unknown during training (i.e., OOD data). While recent advances in vision-language models like CLIP have improved OOD detection, effectively handling the uncertainty inherent in OOD scenarios remains a major challenge, primarily due to the unknown nature, diversity, and absence of OOD samples during training. To address this, we propose a novel method that leverages intuitionistic fuzzy sets (IFS) to explicitly model uncertainty through membership, nonmembership, and hesitation degrees. Specifically, we use a pretrained CLIP-based model to learn positive and negative prompts, which are then used to construct IFS. We further introduce a new loss function to guide the model in building appropriate IFS from ID data, and propose a hesitation-based scoring function for OOD detection during inference. Extensive experiments across standard benchmarks and evaluation metrics show that our approach outperforms state-of-the-art (SOTA) methods, demonstrating the superiority of applying fuzzy logic in addressing the inherent uncertainties of OOD detection.

External IDs:doi:10.1109/tfuzz.2025.3635081