Related papers: Active Self-Training for Weakly Supervised 3D Scen…
Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and…
3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D…
Semantic segmentation on 3D point clouds is an important task for 3D scene understanding. While dense labeling on 3D data is expensive and time-consuming, only a few works address weakly supervised semantic point cloud segmentation methods…
Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…
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…
This paper investigates indoor point cloud semantic segmentation under scene-level annotation, which is less explored compared to methods relying on sparse point-level labels. In the absence of precise point-level labels, current methods…
Current state of the art methods for generating semantic segmentation rely heavily on a large set of images that have each pixel labeled with a class of interest label or background. Coming up with such labels, especially in domains that…
This paper proposes a new active learning method for semantic segmentation. The core of our method lies in a new annotation query design. It samples informative local image regions (e.g., superpixels), and for each of such regions, asks an…
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…
Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes…
Scribble-based weakly supervised semantic segmentation leverages only a few annotated pixels as labels to train a segmentation model, presenting significant potential for reducing the human labor involved in the annotation process. This…
Semantic segmentation has been widely investigated in the community, in which the state of the art techniques are based on supervised models. Those models have reported unprecedented performance at the cost of requiring a large set of high…
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,…
With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…
Manually annotating complex scene point cloud datasets is both costly and error-prone. To reduce the reliance on labeled data, a new model called SnapshotNet is proposed as a self-supervised feature learning approach, which directly works…
Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…
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…
Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired target domain, which only has minimal or no annotations. In…
Deep neural networks usually require accurate and a large number of annotations to achieve outstanding performance in medical image segmentation. One-shot segmentation and weakly-supervised learning are promising research directions that…
High annotation costs are a major bottleneck for the training of semantic segmentation systems. Therefore, methods working with less annotation effort are of special interest. This paper studies the problem of semi-supervised semantic…