相关论文: Fully Convolutional Cross-Scale-Flows for Image-ba…

Modern robotic perception is highly dependent on neural networks. It is well known that neural network-based perception can be unreliable in real-world deployment, especially in difficult imaging conditions. Out-of-distribution detection is…

Defect detection is the task of identifying defects in production samples. Usually, defect detection classifiers are trained on ground-truth data formed by normal samples (negative data) and samples with defects (positive data), where the…

In this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It consists of five…

Unsupervised anomaly detection is coming into the spotlight these days in various practical domains due to the limited amount of anomaly data. One of the major approaches for it is a normalizing flow which pursues the invertible…

Anomaly detection is the process of identifying atypical data samples that significantly deviate from the majority of the dataset. In the realm of clinical screening and diagnosis, detecting abnormalities in medical images holds great…

Detecting surface anomalies of industrial materials poses a significant challenge within a myriad of industrial manufacturing processes. In recent times, various methodologies have emerged, capitalizing on the advantages of employing a…

Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers…

Existing rectified flow models are based on linear trajectories between data and noise distributions. This linearity enforces zero curvature, which can inadvertently force the image generation process through low-probability regions of the…

Traditional deep learning models often lack annotated data, especially in cross-domain applications such as anomaly detection, which is critical for early disease diagnosis in medicine and defect detection in industry. To address this…

Large displacement optical flow is an integral part of many computer vision tasks. Variational optical flow techniques based on a coarse-to-fine scheme interpolate sparse matches and locally optimize an energy model conditioned on colour,…

Many anomaly detection approaches, especially deep learning methods, have been recently developed to identify abnormal image morphology by only employing normal images during training. Unfortunately, many prior anomaly detection methods…

Generative models have gained popularity for their potential applications in imaging science, such as image reconstruction, posterior sampling and data sharing. Flow-based generative models are particularly attractive due to their ability…

Changes, planned or unexpected, are common during the execution of real-life processes. Detecting these changes is a must for optimizing the performance of organizations running such processes. Most of the algorithms present in the…

Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…

Video anomaly detection is an ill-posed problem because it relies on many parameters such as appearance, pose, camera angle, background, and more. We distill the problem to anomaly detection of human pose, thus decreasing the risk of…

Explicitly disentangling style and content in vision models remains challenging due to their semantic overlap and the subjectivity of human perception. Existing methods propose separation through generative or discriminative objectives, but…

Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we…

Automatic defect recognition is one of the research hotspots in steel production, but most of the current methods mainly extract features manually and use machine learning classifiers to recognize defects, which cannot tackle the situation,…

Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains difficult. We propose…

Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…