Visual Tripwires: Anticipating Failure in Deep Vision Systems

2026-09-23

AI Summary

论文提出Visual Tripwires框架，通过监测模型行为的时序不稳定性来预测深度视觉系统的即将发生的故障，比传统方法更早、更准确地发出警告。

Abstract

Deep vision systems remain vulnerable to corruption, occlusion, and distribution shift despite strong benchmark performance. Existing reliability methods typically evaluate uncertainty at individual time steps and do not explicitly model how a system progresses toward failure. We introduce Visual Tripwires, a predictive reliability framework that uses temporal instability in model behaviour to anticipate impending failure. Our central hypothesis is that predictive degradation develops progressively through measurable changes in latent representations, prediction trajectories, and attention structure. Visual Tripwires captures these changes using representation drift, prediction oscillation, trajectory curvature, and attention entropy. A lightweight tripwire predictor aggregates these signals over a temporal window to estimate the probability of failure within a future prediction horizon. Experiments across multiple datasets, architectures, and progressive perturbation settings show that the proposed instability signals emerge before predictive degradation and provide earlier and more accurate failure warnings than conventional uncertainty estimation methods. These results demonstrate that temporal instability contains useful information about future model reliability and provides a practical basis for early warning in deep vision systems.

Problem

• Deep Vision Systems
• Failure Anticipation
• Temporal Instability
• Uncertainty Estimation
• Reliability

Innovation

• Visual Tripwires
• temporal instability
• predictive reliability
• representation drift
• attention entropy