Learning Multi-Manifold Embedding for Out-Of-Distribution Detection
This addresses the need for trustworthy AI in real-world applications by improving OOD detection, though it appears incremental as it builds on existing representation learning and latent embedding techniques.
The paper tackled the problem of out-of-distribution (OOD) detection by introducing a Multi-Manifold Embedding Learning (MMEL) framework, which significantly reduced the false positive rate (FPR) while maintaining high AUC compared to state-of-the-art methods, achieving comparable performance with only ten OOD samples versus 80 million used by other approaches.
Detecting out-of-distribution (OOD) samples is crucial for trustworthy AI in real-world applications. Leveraging recent advances in representation learning and latent embeddings, Various scoring algorithms estimate distributions beyond the training data. However, a single embedding space falls short in characterizing in-distribution data and defending against diverse OOD conditions. This paper introduces a novel Multi-Manifold Embedding Learning (MMEL) framework, optimizing hypersphere and hyperbolic spaces jointly for enhanced OOD detection. MMEL generates representative embeddings and employs a prototype-aware scoring function to differentiate OOD samples. It operates with very few OOD samples and requires no model retraining. Experiments on six open datasets demonstrate MMEL's significant reduction in FPR while maintaining a high AUC compared to state-of-the-art distance-based OOD detection methods. We analyze the effects of learning multiple manifolds and visualize OOD score distributions across datasets. Notably, enrolling ten OOD samples without retraining achieves comparable FPR and AUC to modern outlier exposure methods using 80 million outlier samples for model training.