CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments

• URL: http://arxiv.org/abs/2510.26006v1
• Date: Wed, 29 Oct 2025 22:34:26 GMT
• Title: CAVE: Detecting and Explaining Commonsense Anomalies in Visual Environments
• Abstract summary: We introduce CAVE, the first benchmark of real-world visual anomalies.<n>CAVE supports three open-ended tasks: anomaly description, explanation, and justification.<n>These annotations draw inspiration from cognitive science research on how humans identify and resolve anomalies.
• Score: 34.26006736991816
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection [66.0756595768692]
  We introduce a weakly supervised graph anomaly detection method that leverages a feature learning strategy tailored for graph anomalies.<n>Our approach is built upon a multi-task learning scheme that extracts robust feature representations through synthesized anomalies.<n>Experiments on public datasets demonstrate the superior performance of our method over its competitors.
  arXiv  Detail & Related papers  (2026-05-12T08:27:06Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies [40.03295633717008]
  We introduce VIA-Bench, a benchmark designed to probe model performance on visual illusions and anomalies.<n>We construct over 1K high-quality question-answer pairs that require nuanced visual reasoning.<n>Our findings reveal a fundamental divergence between machine and human perception, suggesting that resolving such perceptual bottlenecks is critical for the advancement of artificial general intelligence.
  arXiv  Detail & Related papers  (2026-02-02T08:48:03Z)
• CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World [23.48765196513229]
  We introduce CueBench, the first of its kind Benchmark devoted to context-aware video anomalies.<n>We propose to unify and benchmark context-aware VAU with various challenging tasks across recognition, temporal grounding, detection, and anticipation.<n>We further develop Cue-R1 based on R1-style reinforcement fine-tuning with verifiable, task-aligned, and hierarchy-refined rewards.
  arXiv  Detail & Related papers  (2025-11-01T16:29:35Z)
• Review of Hallucination Understanding in Large Language and Vision Models [65.29139004945712]
  We present a framework for characterizing both image and text hallucinations across diverse applications.<n>Our investigations reveal that hallucinations often stem from predictable patterns in data distributions and inherited biases.<n>This survey provides a foundation for developing more robust and effective solutions to hallucinations in real-world generative AI systems.
  arXiv  Detail & Related papers  (2025-09-26T09:23:08Z)
• Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models [13.768090541138571]
  Vision Language Models (VLMs) excel at identifying and describing objects but often fail at spatial reasoning.<n>Our analysis reveals a key imbalance: vision token embeddings have much larger norms than text tokens.<n>Tools uncover that vision tokens and system prompts dominate attention.
  arXiv  Detail & Related papers  (2025-03-21T17:51:14Z)
• Enhancing Abnormality Grounding for Vision Language Models with Knowledge Descriptions [11.503540826701807]
  We introduce a novel approach to enhance VLM performance in medical abnormality detection and localization.<n>We focus on breaking down medical concepts into fundamental attributes and common visual patterns.<n>We evaluate our method on the 0.23B Florence-2 base model and demonstrate that it achieves comparable performance in abnormality grounding to significantly larger 7B LLaVA-based medical VLMs.
  arXiv  Detail & Related papers  (2025-03-05T09:02:33Z)
• Exploring What Why and How: A Multifaceted Benchmark for Causation Understanding of Video Anomaly [12.896651217314744]
  We introduce a benchmark for Exploring the Causation of Video Anomalies (ECVA)<n>Our benchmark is meticulously designed, with each video accompanied by detailed human annotations.<n>We propose AnomEval, a specialized evaluation metric crafted to align closely with human judgment criteria for ECVA.
  arXiv  Detail & Related papers  (2024-12-10T04:41:44Z)
• Two Is Better Than One: Aligned Representation Pairs for Anomaly Detection [56.57122939745213]
  Anomaly detection focuses on identifying samples that deviate from the norm.<n>Recent self-supervised methods have successfully learned such representations by employing prior knowledge about anomalies to create synthetic outliers during training.<n>We address this limitation with our new approach Con$$, which leverages prior knowledge about symmetries in normal samples to observe the data in different contexts.
  arXiv  Detail & Related papers  (2024-05-29T07:59:06Z)
• Uncovering What, Why and How: A Comprehensive Benchmark for Causation Understanding of Video Anomaly [29.822544507594056]
  We present a benchmark for Causation Understanding of Video Anomaly (CUVA) Each instance of the proposed benchmark involves three sets of human annotations to indicate the "what", "why" and "how" of an anomaly. MMEval is a novel evaluation metric designed to better align with human preferences for CUVA.
  arXiv  Detail & Related papers  (2024-04-30T20:11:49Z)
• Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach [49.995833831087175]
  This work proposes a novel method for generating generic Video-temporal PAs by inpainting a masked out region of an image. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting. Our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting.
  arXiv  Detail & Related papers  (2023-11-27T13:14:06Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• Unveiling the Unseen: A Comprehensive Survey on Explainable Anomaly Detection in Images and Videos [49.07140708026425]
  Anomaly detection and localization in visual data, including images and videos, are crucial in machine learning and real-world applications.<n>This paper provides the first comprehensive survey focused specifically on explainable 2D visual anomaly detection (X-VAD)<n>We present a literature review of explainable methods, categorized by their underlying techniques.<n>We discuss promising future directions and open problems, including quantifying explanation quality.
  arXiv  Detail & Related papers  (2023-02-13T20:17:41Z)
• Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection [90.32910087103744]
  A few labeled anomaly examples are often available in many real-world applications. These anomaly examples provide valuable knowledge about the application-specific abnormality. Those anomalies seen during training often do not illustrate every possible class of anomaly. This paper tackles open-set supervised anomaly detection.
  arXiv  Detail & Related papers  (2022-03-28T05:21:37Z)
• A Survey of Visual Sensory Anomaly Detection [53.23336329817023]
  Visual sensory anomaly detection (AD) is an essential problem in computer vision. We provide a comprehensive review of visual sensory AD and category into three levels according to the form of anomalies.
  arXiv  Detail & Related papers  (2022-02-14T19:50:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.