CMOOD: Concept-based Multi-label OOD Detection

Understand

How can models effectively detect out-of-distribution (OOD) samples in complex, multi-label settings without extensive retraining? Existing OOD detection methods struggle to capture the intricate semantic relationships and label co-occurrences inherent in multi-label settings, often requiring large amounts of training data and failing to generalize to unseen label combinations.

• While large language models have revolutionized zero-shot OOD detection, they primarily focus on single-label scenarios, leaving a critical gap in handling real-world tasks where samples can be associated with multiple interdependent labels.
• To address these challenges, we introduce COOD, a novel zero-shot multi-label OOD detection framework.
• COOD leverages pre-trained vision-language models, enhancing them with a concept-based label expansion strategy and a new scoring function.