相关论文: SubspaceAD: Training-Free Few-Shot Anomaly Detecti…

This paper explores the problem of Generalist Anomaly Detection (GAD), aiming to train one single detection model that can generalize to detect anomalies in diverse datasets from different application domains without any further training on…

Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings, insufficient training samples often fail to cover the…

Precise anomaly detection in medical images is critical for clinical decision-making. While recent unsupervised or semi-supervised anomaly detection methods trained on large-scale normal data show promising results, they lack fine-grained…

Graph anomaly detection (GAD) is critical for identifying abnormal nodes in graph-structured data from diverse domains, including cybersecurity and social networks. The existing GAD methods often focus on the learning paradigms of…

Zero-shot anomaly detection (ZSAD) methods entail detecting anomalies directly without access to any known normal or abnormal samples within the target item categories. Existing approaches typically rely on the robust generalization…

Zero-shot anomaly classification (AC) and segmentation (AS) methods aim to identify and outline defects without using any labeled samples. In this paper, we reveal a key property that is overlooked by existing methods: normal image patches…

This paper considers zero-shot Anomaly Detection (AD), performing AD without reference images of the test objects. We propose a framework called CLIP-AD to leverage the zero-shot capabilities of the large vision-language model CLIP.…

Zero-Shot Anomaly Detection (ZSAD) seeks to identify anomalies from arbitrary novel categories, offering a scalable and annotation-efficient solution. Traditionally, most ZSAD works have been based on the CLIP model, which performs anomaly…

Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in…

Few-shot graph anomaly detection (GAD) has recently garnered increasing attention, which aims to discern anomalous patterns among abundant unlabeled test nodes under the guidance of a limited number of labeled training nodes. Existing…

We address the problem of anomaly detection in videos. The goal is to identify unusual behaviours automatically by learning exclusively from normal videos. Most existing approaches are usually data-hungry and have limited generalization…

Efficient evaluation of a network architecture drawn from a large search space remains a key challenge in Neural Architecture Search (NAS). Vanilla NAS evaluates each architecture by training from scratch, which gives the true performance…

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…

Few-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. To alleviate the constraint of few samples, enhancing the generalization ability of learned features for novel objects…

Few-shot anomaly detection (FSAD) methods identify anomalous regions with few known normal samples. Most existing methods rely on the generalization ability of pre-trained vision-language models (VLMs) to recognize potentially anomalous…

Current anomaly detection methods primarily focus on low-resolution scenarios. For high-resolution images, conventional downsampling often results in missed detections of subtle anomalous regions due to the loss of fine-grained…

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.…

Traditional Anomaly Detection (AD) methods have predominantly relied on unsupervised learning from extensive normal data. Recent AD methods have evolved with the advent of large pre-trained vision-language models, enhancing few-shot anomaly…

Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches…

In this paper, we present FSOD-VFM: Few-Shot Object Detectors with Vision Foundation Models, a framework that leverages vision foundation models to tackle the challenge of few-shot object detection. FSOD-VFM integrates three key components:…