Related papers: PDF: A Probability-Driven Framework for Open World…

3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning. Recent advances in deep learning have significantly enhanced fully supervised medical image segmentation. However,…

Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…

Quantitatively connecting properties of parton distribution functions (PDFs, or parton densities) to the theoretical assumptions made within the QCD analyses which produce them has been a longstanding problem in HEP phenomenology. To…

Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language…

Open-set panoptic segmentation (OPS) problem is a new research direction aiming to perform segmentation for both \known classes and \unknown classes, i.e., the objects ("things") that are never annotated in the training set. The main…

In domain generalization, the knowledge learnt from one or multiple source domains is transferred to an unseen target domain. In this work, we propose a novel domain generalization approach for fine-grained scene recognition. We first…

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)…

Understanding point clouds is of great importance. Many previous methods focus on detecting salient keypoints to identity structures of point clouds. However, existing methods neglect the semantics of points selected, leading to poor…

Semi-weakly supervised semantic segmentation (SWSSS) aims to train a model to identify objects in images based on a small number of images with pixel-level labels, and many more images with only image-level labels. Most existing SWSSS…

Unsupervised domain adaptation (UDA) methods have been broadly utilized to improve the models' adaptation ability in general computer vision. However, different from the natural images, there exist huge semantic gaps for the nuclei from…

Semantic segmentation of LiDAR point clouds is an important task in autonomous driving. However, training deep models via conventional supervised methods requires large datasets which are costly to label. It is critical to have…

3D semantic segmentation is a fundamental building block for several scene understanding applications such as autonomous driving, robotics and AR/VR. Several state-of-the-art semantic segmentation models suffer from the part…

Deep neural networks have made breakthroughs in a wide range of visual understanding tasks. A typical challenge that hinders their real-world applications is that unknown samples may be fed into the system during the testing phase, but…

Few shot segmentation (FSS) aims to learn pixel-level classification of a target object in a query image using only a few annotated support samples. This is challenging as it requires modeling appearance variations of target objects and the…

Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively…

In this paper, we present the PS^2-Net -- a locally and globally aware deep learning framework for semantic segmentation on 3D scene-level point clouds. In order to deeply incorporate local structures and global context to support 3D scene…

An understanding and classification of driving scenarios are important for testing and development of autonomous driving functionalities. Machine learning models are useful for scenario classification but most of them assume that data…

Even as deep neural networks have become very effective for tasks in vision and perception, it remains difficult to explain and debug their behavior. In this paper, we present a programmatic and semantic approach to explaining,…

Segmentation is a crucial analysis task in biomedical imaging. Given the diverse experimental settings in this field, the lack of generalization limits the use of deep learning in practice. Domain adaptation is a promising remedy: it…

Unsupervised domain adaptation (UDA) for semantic segmentation aims to transfer the pixel-wise knowledge from the labeled source domain to the unlabeled target domain. However, current UDA methods typically assume a shared label space…