CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments
This addresses the problem of limited anomaly detection in computer vision for researchers, providing a realistic benchmark to advance commonsense reasoning in VLMs, though it is incremental as it builds on existing VLM frameworks.
The authors tackled the challenge of detecting and explaining real-world visual anomalies by introducing CAVE, the first benchmark for this task, and found that state-of-the-art Vision-Language Models struggle with it, achieving low performance even with advanced prompting.
Humans can naturally identify, reason about, and explain anomalies in their environment. In computer vision, this long-standing challenge remains limited to industrial defects or unrealistic, synthetically generated anomalies, failing to capture the richness and unpredictability of real-world anomalies. In this work, we introduce CAVE, the first benchmark of real-world visual anomalies. CAVE supports three open-ended tasks: anomaly description, explanation, and justification; with fine-grained annotations for visual grounding and categorizing anomalies based on their visual manifestations, their complexity, severity, and commonness. These annotations draw inspiration from cognitive science research on how humans identify and resolve anomalies, providing a comprehensive framework for evaluating Vision-Language Models (VLMs) in detecting and understanding anomalies. We show that state-of-the-art VLMs struggle with visual anomaly perception and commonsense reasoning, even with advanced prompting strategies. By offering a realistic and cognitively grounded benchmark, CAVE serves as a valuable resource for advancing research in anomaly detection and commonsense reasoning in VLMs.