Training-Free Out-Of-Distribution Segmentation With Foundation Models

Detecting unknown objects in semantic segmentation is crucial for safety-critical applications such as autonomous driving. Large vision foundation models, includ- ing DINOv2, InternImage, and CLIP, have advanced visual representation learn- ing by providing rich features that generalize well across diverse tasks. While their strength in closed-set semantic tasks is established, their capability to detect out- of-distribution (OoD) regions in semantic segmentation remains underexplored. In this work, we investigate whether foundation models fine-tuned on segmen- tation datasets can inherently distinguish in-distribution (ID) from OoD regions without any outlier supervision. We propose a simple, training-free approach that utilizes features from the InternImage backbone and applies K-Means clustering alongside confidence thresholding on raw decoder logits to identify OoD clusters. Our method achieves 50.02 Average Precision on the RoadAnomaly benchmark and 48.77 on the benchmark of ADE-OoD with InternImage-L, surpassing several supervised and unsupervised baselines. These results suggest a promising direc- tion for generic OoD segmentation methods that require minimal assumptions or additional data.