Related papers: ALISE: Annotation-Free LiDAR Instance Segmentation…

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored…

In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method which leverages on moving a 2D camera by means of a robot, proving precise camera tracking, and an augmented reality pen to define initial…

Standard segmentation of medical images based on full-supervised convolutional networks demands accurate dense annotations. Such learning framework is built on laborious manual annotation with restrict demands for expertise, leading to…

Dominated point cloud-based 3D object detectors in autonomous driving scenarios rely heavily on the huge amount of accurately labeled samples, however, 3D annotation in the point cloud is extremely tedious, expensive and time-consuming. To…

Moving object segmentation is a crucial task for safe and reliable autonomous mobile systems like self-driving cars, improving the reliability and robustness of subsequent tasks like SLAM or path planning. While the segmentation of camera…

Autonomous vehicles drive millions of miles on the road each year. Under such circumstances, deployed machine learning models are prone to failure both in seemingly normal situations and in the presence of outliers. However, in the training…

Semantic segmentation of 3D point cloud data often comes with high annotation costs. Active learning automates the process of selecting which data to annotate, reducing the total amount of annotation needed to achieve satisfactory…

Poles and building edges are frequently observable objects on urban roads, conveying reliable hints for various computer vision tasks. To repetitively extract them as features and perform association between discrete LiDAR frames for…

Instance segmentation on 3D point clouds (3DIS) is a longstanding challenge in computer vision, where state-of-the-art methods are mainly based on full supervision. As annotating ground truth dense instance masks is tedious and expensive,…

Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development. However, generating exhaustive and accurate…

3D weakly supervised semantic segmentation (3D WSSS) aims to achieve semantic segmentation by leveraging sparse or low-cost annotated data, significantly reducing reliance on dense point-wise annotations. Previous works mainly employ class…

Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…

Automated vehicles rely on an accurate and robust perception of the environment. Similarly to automated cars, highly automated trains require an environmental perception. Although there is a lot of research based on either camera or LiDAR…

Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have emerged tackling this problem in an unsupervised fashion.…

One key bottleneck of employing state-of-the-art semantic segmentation networks in the real world is the availability of training labels. Conventional semantic segmentation networks require massive pixel-wise annotated labels to reach…

Semantic segmentation of SAR images has garnered significant attention in remote sensing due to the immunity of SAR sensors to cloudy weather and light conditions. Nevertheless, SAR imagery lacks detailed information and is plagued by…

Semantic segmentation of 3D LiDAR point clouds is important in urban remote sensing for understanding real-world street environments. This task, by projecting LiDAR point clouds and 3D semantic labels as sparse maps, can be reformulated as…

Vehicle re-identification (reID) aims at identifying vehicles across different non-overlapping cameras views. The existing methods heavily relied on well-labeled datasets for ideal performance, which inevitably causes fateful drop due to…

In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Detecting cells as a first step, a cell expert evaluates the growth of cells according to cytotoxicity grade under the microscope. Thus, human fatigue…