Related papers: Anomaly-Aware Semantic Segmentation by Leveraging …

Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the…

Most of the existing methods for anomaly detection use only positive data to learn the data distribution, thus they usually need a pre-defined threshold at the detection stage to determine whether a test instance is an outlier.…

Semantic segmentation approaches are typically trained on large-scale data with a closed finite set of known classes without considering unknown objects. In certain safety-critical robotics applications, especially autonomous driving, it is…

Recent efforts in deploying Deep Neural Networks for object detection in real world applications, such as autonomous driving, assume that all relevant object classes have been observed during training. Quantifying the performance of these…

Anomaly detection under open-set scenario is a challenging task that requires learning discriminative fine-grained features to detect anomalies that were even unseen during training. As a cheap yet effective approach, data augmentation has…

In order to navigate safely and reliably in off-road and unstructured environments, robots must detect anomalies that are out-of-distribution (OOD) with respect to the training data. We present an analysis-by-synthesis approach for…

Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…

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…

Deep learning-based approaches achieve state-of-the-art performance in the majority of image segmentation benchmarks. However, training of such models requires a sizable amount of manual annotations. In order to reduce this effort, we…

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…

Anomaly detection plays a vital role in industrial manufacturing. Due to the scarcity of real defect images, unsupervised approaches that rely solely on normal images have been extensively studied. Recently, diffusion-based generative…

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high…

Anomaly segmentation is a crucial task for safety-critical applications, such as autonomous driving in urban scenes, where the goal is to detect out-of-distribution (OOD) objects with categories which are unseen during training. The core…

Anomaly detection is often considered a challenging field of machine learning due to the difficulty of obtaining anomalous samples for training and the need to obtain a sufficient amount of training data. In recent years, autoencoders have…

Semi-supervised Learning plays a crucial role in network anomaly detection applications, however, learning anomaly patterns with limited labeled samples is not easy. Additionally, the lack of interpretability creates key barriers to the…

Medical imaging data suffers from the limited availability of annotation because annotating 3D medical data is a time-consuming and expensive task. Moreover, even if the annotation is available, supervised learning-based approaches suffer…

Semantic segmentation is a key technique that enables mobile robots to understand and navigate surrounding environments autonomously. However, most existing works focus on segmenting known objects, overlooking the identification of unknown…

Anomaly detection plays a key role in industrial manufacturing for product quality control. Traditional methods for anomaly detection are rule-based with limited generalization ability. Recent methods based on supervised deep learning are…

With the availability of many datasets tailored for autonomous driving in real-world urban scenes, semantic segmentation for urban driving scenes achieves significant progress. However, semantic segmentation for off-road, unstructured…

Synthesizing realistic and diverse anomalous samples from limited data is vital for robust model generalization. However, existing methods struggle to reconcile fidelity and diversity, often hampered by distribution misalignment and…