Related papers: Guided Curriculum Model Adaptation and Uncertainty…
While recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training),…
In this work, we for the first time present a method for detecting label errors in image datasets with semantic segmentation, i.e., pixel-wise class labels. Annotation acquisition for semantic segmentation datasets is time-consuming and…
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles. To acquire a complete $180^\circ$ semantic understanding of the forward surroundings, we…
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…
Image segmentation is a critical step in computational biomedical image analysis, typically evaluated using metrics like the Dice coefficient during training and validation. However, in clinical settings without manual annotations,…
Using deep learning, we now have the ability to create exceptionally good semantic segmentation systems; however, collecting the prerequisite pixel-wise annotations for training images remains expensive and time-consuming. Therefore, it…
The learning order of semantic classes significantly impacts unsupervised domain adaptation for semantic segmentation, especially under adverse weather conditions. Most existing curricula rely on handcrafted heuristics (e.g., fixed…
The uncertainty quantification of sensor measurements coupled with deep learning networks is crucial for many robotics systems, especially for safety-critical applications such as self-driving cars. This paper develops an uncertainty…
Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…
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…
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…
Most state-of-the-art semantic segmentation approaches only achieve high accuracy in good conditions. In practically-common but less-discussed adverse environmental conditions, their performance can decrease enormously. Existing studies…
Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…
Medical image segmentation is a fundamental and critical step in many clinical approaches. Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring…
Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC)…
Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present…
The performance of nighttime semantic segmentation is restricted by the poor illumination and a lack of pixel-wise annotation, which severely limit its application in autonomous driving. Existing works, e.g., using the twilight as the…
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we…
Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated…
Autonomous vehicles and driving systems use scene parsing as an essential tool to understand the surrounding environment. Panoptic segmentation is a state-of-the-art technique which proves to be pivotal in this use case. Deep learning-based…