Related papers: Towards Zero-Shot Anomaly Detection and Reasoning …
Video Anomaly Detection (VAD) is crucial for applications such as security surveillance and autonomous driving. However, existing VAD methods provide little rationale behind detection, hindering public trust in real-world deployments. In…
Time series anomaly detection (TSAD) has been a long-standing pillar problem in Web-scale systems and online infrastructures, such as service reliability monitoring, system fault diagnosis, and performance optimization. Large language…
Large Vision-Language Models (LVLMs) such as MiniGPT-4 and LLaVA have demonstrated the capability of understanding images and achieved remarkable performance in various visual tasks. Despite their strong abilities in recognizing common…
Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring. Within natural language processing (NLP), AD helps detect issues like spam,…
Semantic segmentation networks have achieved significant success under the assumption of independent and identically distributed data. However, these networks often struggle to detect anomalies from unknown semantic classes due to the…
Visual anomaly detection is vital in real-world applications, such as industrial defect detection and medical diagnosis. However, most existing methods focus on local structural anomalies and fail to detect higher-level functional anomalies…
Zero-shot 3D (ZS-3D) anomaly detection aims to identify defects in 3D objects without relying on labeled training data, making it especially valuable in scenarios constrained by data scarcity, privacy, or high annotation cost. However, most…
Unsupervised visual anomaly detection from multi-view images presents a significant challenge: distinguishing genuine defects from benign appearance variations caused by viewpoint changes. Existing methods, often designed for single-view…
Current Zero-Shot Learning (ZSL) approaches are restricted to recognition of a single dominant unseen object category in a test image. We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear…
Zero-Shot Anomaly Detection (ZSAD) leverages Vision-Language Models (VLMs) to enable supervision-free industrial inspection. However, existing ZSAD paradigms are constrained by single visual backbones, which struggle to balance global…
Detecting anomalous hazards in visual data, particularly in video streams, is a critical challenge in autonomous driving. Existing models often struggle with unpredictable, out-of-label hazards due to their reliance on predefined object…
Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but…
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. However, current approaches are inherently limited to a…
Video anomaly detection (VAD) aims to identify unexpected events in videos and has wide applications in safety-critical domains. While semi-supervised methods trained on only normal samples have gained traction, they often suffer from high…
Large multimodal models (LMMs) exhibit strong task generalization capabilities, offering new opportunities for zero-shot visual anomaly segmentation (ZSAS). However, existing LMM-based segmentation approaches still face fundamental…
Recent advances in industrial anomaly detection have highlighted the need for deeper logical anomaly analysis, where unexpected relationships among objects, counts, and spatial configurations must be identified and explained. Existing…
As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To solve it, the few-shot anomaly detection (FSAD) scheme is…
Zero-shot anomaly detection aims to identify defects in unseen categories without target-specific training. Existing methods usually apply the same feature transformation to all samples, treating normal and anomalous data uniformly despite…
Recent advancements in reasoning capability of Multimodal Large Language Models (MLLMs) demonstrate its effectiveness in tackling complex visual tasks. However, existing MLLM-based Video Anomaly Detection (VAD) methods remain limited to…
Zero-Shot Video Anomaly Detection (ZS-VAD) requires temporally localizing anomalies without target domain training data, which is a crucial task due to various practical concerns, e.g., data privacy or new surveillance deployments.…