DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection

Understand

Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution.

• While traditional OOD detection has primarily focused on single-modality inputs, such as images, recent advances in multimodal models have demonstrated the potential of leveraging multiple modalities (e.g., video, optical flow, audio) to enhance detection performance.
• However, existing methods often overlook intra-class variability within in-distribution (ID) data, assuming that samples of the same class are perfectly cohesive and consistent.
• This assumption can lead to performance degradation, especially when prediction discrepancies are uniformly amplified across all samples.