Rarity-Gated Context Conditioning for Offline Imitation Learning-Based Maritime Anomaly Detection

2026-06-11

AI Summary

This work addresses the high false alarm rate and unstable decision-making in anomaly detection under rare contextual scenarios, which arise from severe context imbalance. To mitigate this issue, the authors propose a context rarity-aware feature modulation mechanism that integrates a data-driven rarity scoring gate within an offline imitation learning framework. Specifically, Rarity-Gated Feature-wise Linear Modulation (RGFiLM) dynamically adjusts intermediate feature representations based on contextual rarity, while jointly incorporating AIS trajectory sequences and ERA5 environmental context. Experimental results demonstrate that the proposed method significantly outperforms existing context-agnostic and context-conditioned approaches in maritime trajectory anomaly detection, achieving superior overall performance in terms of both F1 score and false positive rate.

Abstract

Contextual anomaly detection aims to identify abnormal behavior conditional on context variables, but practical deployments often face highly imbalanced context distributions where rare regimes can be critical information. Under such frequency bias, context-conditioned models can produce unstable decisions and excessive false alarms in rare contexts. We propose Rarity-Gated Feature-wise Linear Modulation (RGFiLM), a rarity-aware conditioning module that combines feature-wise modulation (i.e., context-conditioned scaling and shifting of hidden features) with a gate controlled by a data-driven rarity score. The rarity score is estimated from the empirical distribution of context variables and regulates how strongly context modulates intermediate representations: the gate becomes more decisive under rare contexts while remaining conservative under frequent contexts. We evaluate RGFiLM on maritime trajectory anomaly detection using AIS motion sequences with ERA5 environmental context in an environment-sensitive detour scenario. When instantiated in a sequential anomaly scoring pipeline, RGFiLM achieves the best mean F1--False Positive Rate (FPR) trade-off among the compared context-agnostic and context-conditioned methods. These results suggest that explicitly accounting for context rarity is an effective approach for reducing false alarms in context-sensitive anomaly detection.

Problem

• contextual anomaly detection
• class imbalance
• rare contexts
• false alarms
• offline imitation learning

Innovation

• Rarity-Gated FiLM
• context-conditioned anomaly detection
• offline imitation learning
• maritime anomaly detection
• rarity-aware modulation