Related papers: Maskomaly:Zero-Shot Mask Anomaly Segmentation

Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalies). This is especially important for scene understanding…

The representative instance segmentation methods mostly segment different object instances with a mask of the fixed resolution, e.g., 28*28 grid. However, a low-resolution mask loses rich details, while a high-resolution mask incurs…

Nuclei segmentation is a fundamental task in digital pathology analysis and can be automated by deep learning-based methods. However, the development of such an automated method requires a large amount of data with precisely annotated masks…

We introduce a neural network framework, utilizing adversarial learning to partition an image into two cuts, with one cut falling into a reference distribution provided by the user. This concept tackles the task of unsupervised anomaly…

Semantic amodal segmentation is a recently proposed extension to instance-aware segmentation that includes the prediction of the invisible region of each object instance. We present the first all-in-one end-to-end trainable model for…

We present a new, embarrassingly simple approach to instance segmentation in images. Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that have made instance segmentation…

Automatic skin lesion segmentation on dermoscopic images is an essential component in computer-aided diagnosis of melanoma. Recently, many fully supervised deep learning based methods have been proposed for automatic skin lesion…

As a computer vision task, automatic object segmentation remains challenging in specialized image domains without massive labeled data, such as synthetic aperture sonar images, remote sensing, biomedical imaging, etc. In any domain,…

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accuracy often falls…

Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent…

Segment anything model (SAM) has emerged as the leading approach for zero-shot learning in segmentation tasks, offering the advantage of avoiding pixel-wise annotations. It is particularly appealing in medical image segmentation, where the…

This paper introduces a novel anomaly detection framework that combines the robust statistical principles of density-estimation-based anomaly detection methods with the representation-learning capabilities of deep learning models. The…

As one of the most challenging and practical segmentation tasks, open-world semantic segmentation requires the model to segment the anomaly regions in the images and incrementally learn to segment out-of-distribution (OOD) objects,…

This paper explores the use of a soft ground-truth mask ("soft mask'') to train a Fully Convolutional Neural Network (FCNN) for segmentation of Multiple Sclerosis (MS) lesions. Detection and segmentation of MS lesions is a complex task…

Unsupervised anomaly detection is a challenging task in industrial applications since it is impracticable to collect sufficient anomalous samples. In this paper, a novel Self-Supervised Guided Segmentation Framework (SGSF) is proposed by…

This paper presents the first application of neural architecture search to the complex task of segmenting visual anomalies. Measurement of anomaly segmentation performance is challenging due to imbalanced anomaly pixels, varying region…

Unsupervised approaches for video anomaly detection may not perform as good as supervised approaches. However, learning unknown types of anomalies using an unsupervised approach is more practical than a supervised approach as annotation is…

Anomaly detection becomes increasingly important for the dependability and serviceability of IT services. As log lines record events during the execution of IT services, they are a primary source for diagnostics. Thereby, unsupervised…

Uniform downsampling remains the de facto standard for reducing spatial resolution in vision backbones. In this work, we propose an alternative design built around a content-aware spatial grouping layer, that dynamically assigns tokens to a…

Current unsupervised anomaly localization approaches rely on generative models to learn the distribution of normal images, which is later used to identify potential anomalous regions derived from errors on the reconstructed images. However,…