Related papers: Mask2Anomaly: Mask Transformer for Universal Open-…

Anomaly segmentation is a critical task for driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without considering their contextual semantics…

Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing…

Partially-supervised instance segmentation is a task which requests segmenting objects from novel unseen categories via learning on limited seen categories with annotated masks thus eliminating demands of heavy annotation burden. The key to…

A single unexpected object on the road can cause an accident or may lead to injuries. To prevent this, we need a reliable mechanism for finding anomalous objects on the road. This task, called anomaly segmentation, can be a stepping stone…

In panoptic segmentation, individual instances must be separated within semantic classes. As state-of-the-art methods rely on a pre-defined set of classes, they struggle with novel categories and out-of-distribution (OOD) data. This is…

We present a simple and practical framework for anomaly segmentation called Maskomaly. It builds upon mask-based standard semantic segmentation networks by adding a simple inference-time post-processing step which leverages the raw mask…

Image anomaly detection consists in detecting images or image portions that are visually different from the majority of the samples in a dataset. The task is of practical importance for various real-life applications like biomedical image…

The inability of state-of-the-art semantic segmentation methods to detect anomaly instances hinders them from being deployed in safety-critical and complex applications, such as autonomous driving. Recent approaches have focused on either…

Modern approaches typically formulate semantic segmentation as a per-pixel classification task, while instance-level segmentation is handled with an alternative mask classification. Our key insight: mask classification is sufficiently…

Safe autonomous systems in complex environments require robust road anomaly segmentation to identify unknown obstacles. However, existing approaches often rely on pixel-level statistics to determine whether a region appears anomalous. This…

Panoptic segmentation is a fundamental task in computer vision and a crucial component for perception in autonomous vehicles. Recent mask-transformer-based methods achieve impressive performance on standard benchmarks but face significant…

Perception is a key building block of autonomously acting vision systems such as autonomous vehicles. It is crucial that these systems are able to understand their surroundings in order to operate safely and robustly. Additionally,…

Semantic segmentation models, while effective for in-distribution categories, face challenges in real-world deployment due to encountering out-of-distribution (OoD) objects. Detecting these OoD objects is crucial for safety-critical…

The detection of unknown traffic obstacles is vital to ensure safe autonomous driving. The standard object-detection methods cannot identify unknown objects that are not included under predefined categories. This is because object-detection…

Anomaly awareness is an essential capability for safety-critical applications such as autonomous driving. While recent progress of robotics and computer vision has enabled anomaly detection for image classification, anomaly detection on…

Detecting anomalies in traffic scenes is crucial for ensuring safety in autonomous driving, yet collecting representative anomalous data remains challenging. Existing anomaly detection methods are highly specialized and rely on normality as…

Dealing with atypical traffic scenarios remains a challenging task in autonomous driving. However, most anomaly detection approaches cannot be trained on raw sensor data but require exposure to outlier data and powerful semantic…

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle previously-unseen objects. However, detecting and localizing…

This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires…

Unsupervised anomaly segmentation approaches to pathology segmentation train a model on images of healthy subjects, that they define as the 'normal' data distribution. At inference, they aim to segment any pathologies in new images as…