Related papers: COLA: COarse LAbel pre-training for 3D semantic se…

Accurate segmentation of multiple organs in Computed Tomography (CT) images plays a vital role in computer-aided diagnosis systems. While various supervised learning approaches have been proposed recently, these methods heavily depend on a…

Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is especially important for semantic segmentation tasks involving 3D datasets that are often significantly…

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g.,…

Instance segmentation of unknown objects from images is regarded as relevant for several robot skills including grasping, tracking and object sorting. Recent results in computer vision have shown that large hand-labeled datasets enable high…

Cloud analysis is a critical component of weather and climate science, impacting various sectors like disaster management. However, achieving fine-grained cloud analysis, such as cloud segmentation, in remote sensing remains challenging due…

Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware. Distillation from a trained source model may represent a solution for the first but does not…

Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely…

3D semantic occupancy prediction offers an intuitive and efficient scene understanding and has attracted significant interest in autonomous driving perception. Existing approaches either rely on full supervision, which demands costly…

High-quality pixel-level annotations of medical images are essential for supervised segmentation tasks, but obtaining such annotations is costly and requires medical expertise. To address this challenge, we propose a novel coarse-to-fine…

During the last few years, continual learning (CL) strategies for image classification and segmentation have been widely investigated designing innovative solutions to tackle catastrophic forgetting, like knowledge distillation and…

A main bottleneck of learning-based robotic scene understanding methods is the heavy reliance on extensive annotated training data, which often limits their generalization ability. In LiDAR panoptic segmentation, this challenge becomes even…

In recent years, deep learning has become a breakthrough technique in assisting medical image diagnosis. Supervised learning using convolutional neural networks (CNN) provides state-of-the-art performance and has served as a benchmark for…

Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags. This assumption, however, is impractical for learning fine-grained…

Sclera segmentation is crucial for developing automatic eye-related medical computer-aided diagnostic systems, as well as for personal identification and verification, because the sclera contains distinct personal features. Deep…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…

State-of-the-art 3D object detectors are often trained on massive labeled datasets. However, annotating 3D bounding boxes remains prohibitively expensive and time-consuming, particularly for LiDAR. Instead, recent works demonstrate that…

Recent advances in Vision-Language-Action (VLA) models have shown promise for robot control, but their dependence on action supervision limits scalability and generalization. To address this challenge, we introduce CARE, a novel framework…

This article presents a complete semantic scene understanding workflow using only a single 2D lidar. This fills the gap in 2D lidar semantic segmentation, thereby enabling the rethinking and enhancement of existing 2D lidar-based algorithms…