GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection
This addresses a practical problem for users needing flexible detection in real-world images with multiple objects, representing an incremental improvement over prior work.
The paper tackles zero-shot out-of-distribution detection in multi-object scenarios, where existing methods fail, and shows that GL-MCM outperforms baseline zero-shot methods and is comparable to fully supervised methods on benchmarks like ImageNet.
Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global and local visual features. Due to the simple ensemble score function design, GL-MCM can control the type of ID images with a single weight parameter. Experiments on ImageNet and multi-object benchmarks demonstrate that GL-MCM outperforms baseline zero-shot methods and is comparable to fully supervised methods. Furthermore, GL-MCM offers strong flexibility in adjusting the target type of ID images. The code is available via https://github.com/AtsuMiyai/GL-MCM.