1) The document proposes a simple method called Standardized Max Logits (SML) to detect unexpected road obstacles in semantic segmentation. SML normalizes the maximum logit values for each class to account for differences between in-distribution classes and better identify anomalies.
2) SML is combined with iterative boundary suppression and dilated smoothing techniques to gradually remove false positives and negatives, especially around boundaries.
3) Experiments on three datasets demonstrate SML achieves state-of-the-art performance in detecting anomalies without requiring retraining or additional out-of-distribution data, while maintaining efficient computation.
Related topics: