Related papers: ProPanDL: A Modular Architecture for Uncertainty-A…

In recent years, deep neural networks have defined the state-of-the-art in semantic segmentation where their predictions are constrained to a predefined set of semantic classes. They are to be deployed in applications such as automated…

In semi-supervised medical image segmentation, most previous works draw on the common assumption that higher entropy means higher uncertainty. In this paper, we investigate a novel method of estimating uncertainty. We observe that, when…

Semi-supervised learning relaxes the need of large pixel-wise labeled datasets for image segmentation by leveraging unlabeled data. A prominent way to exploit unlabeled data is to regularize model predictions. Since the predictions of…

Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…

Active Learning (AL) for semantic segmentation is challenging due to heavy class imbalance and different ways of defining "sample" (pixels, areas, etc.), leaving the interpretation of the data distribution ambiguous. We propose…

For navigation of robots, image segmentation is an important component to determining a terrain's traversability. For safe and efficient navigation, it is key to assess the uncertainty of the predicted segments. Current uncertainty…

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…

To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segmentation methods, the…

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly…

In recent years, Convolutional Neural Networks (CNNs) have enabled significant advancements to the state-of-the-art in computer vision. For classification tasks, CNNs have widely employed probabilistic output and have shown the significance…

The use of deep learning for medical imaging has seen tremendous growth in the research community. One reason for the slow uptake of these systems in the clinical setting is that they are complex, opaque and tend to fail silently. Outside…

In this work, we introduce panoramic panoptic segmentation as the most holistic scene understanding both in terms of field of view and image level understanding for standard camera based input. A complete surrounding understanding provides…

Time series forecasting in real-world applications requires both high predictive accuracy and interpretable uncertainty quantification. Traditional point prediction methods often fail to capture the inherent uncertainty in time series data,…

Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task. However, the performance of panoptic segmentation is severely impacted in the presence of…

Encoder-Decoder networks such as U-Nets have been applied successfully in a wide range of computer vision tasks, especially for image segmentation of different flavours across different fields. Nevertheless, most applications lack of a…

This paper proposes a probabilistic deep metric learning (PDML) framework for hyperspectral image classification, which aims to predict the category of each pixel for an image captured by hyperspectral sensors. The core problem for…

Uncertainty maps highlight unreliable regions in segmentation predictions. However, most uncertainty evaluation metrics treat voxels independently, ignoring spatial context and anatomical structure. As a result, they may assign identical…

Panoptic segmentation is a complex full scene parsing task requiring simultaneous instance and semantic segmentation at high resolution. Current state-of-the-art approaches cannot run in real-time, and simplifying these architectures to…

Despite recent advances in the accuracy of brain tumor segmentation, the results still suffer from low reliability and robustness. Uncertainty estimation is an efficient solution to this problem, as it provides a measure of confidence in…

Panoptic segmentation combines instance and semantic predictions, allowing the detection of "things" and "stuff" simultaneously. Effectively approaching panoptic segmentation in remotely sensed data can be auspicious in many challenging…