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

Open-Vocabulary Segmentation (OVS) methods offer promising capabilities in detecting unseen object categories, but the category must be known and needs to be provided by a human, either via a text prompt or pre-labeled datasets, thus…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

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…

Advanced Driver-Assistance Systems (ADAS) have successfully integrated learning-based techniques into vehicle perception and decision-making. However, their application in 3D lane detection for effective driving environment perception is…

Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Nevertheless, most existing methods depend on precise pixel-level annotations by medical professionals, a process that is both costly and…

Although recently several foundation models for satellite remote sensing imagery have been proposed, they fail to address major challenges of real/operational applications. Indeed, embeddings that don't take into account the spectral,…

In response to the growing demand for 3D object detection in applications such as autonomous driving, robotics, and augmented reality, this work focuses on the evaluation of semi-supervised learning approaches for point cloud data. The…

Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint is to implement weakly-supervised pipelines trained with…

State-of-the-art lidar panoptic segmentation (LPS) methods follow bottom-up segmentation-centric fashion wherein they build upon semantic segmentation networks by utilizing clustering to obtain object instances. In this paper, we re-think…

Data collection for autonomous driving is rapidly accelerating, but manual annotation, especially for 3D labels, remains a major bottleneck due to its high cost and labor intensity. Autolabeling has emerged as a scalable alternative,…

We address the problem of unsupervised semantic segmentation of outdoor LiDAR point clouds in diverse traffic scenarios. The key idea is to leverage the spatiotemporal nature of a dynamic point cloud sequence and introduce drastically…

Brain tumor segmentation is important for diagnosis of the tumor, and current deep-learning methods rely on a large set of annotated images for training, with high annotation costs. Unsupervised segmentation is promising to avoid human…

While LiDAR data acquisition is easy, labeling for semantic segmentation remains highly time consuming and must therefore be done selectively. Active learning (AL) provides a solution that can iteratively and intelligently label a dataset…

Current methods for 3D semantic segmentation propose training models with limited annotations to address the difficulty of annotating large, irregular, and unordered 3D point cloud data. They usually focus on the 3D domain only, without…

Semantic Segmentation is one of the most challenging vision tasks, usually requiring large amounts of training data with expensive pixel level annotations. With the success of foundation models and especially vision-language models, recent…

We introduce ASIA (Adaptive 3D Segmentation using few Image Annotations), a novel framework that enables segmentation of possibly non-semantic and non-text-describable "parts" in 3D. Our segmentation is controllable through a few…

Understanding motion in dynamic environments is critical for autonomous driving, thereby motivating research on class-agnostic motion prediction. In this work, we investigate weakly and self-supervised class-agnostic motion prediction from…

Current 3D object detectors for autonomous driving are almost entirely trained on human-annotated data. Although of high quality, the generation of such data is laborious and costly, restricting them to a few specific locations and object…

Deep-learning-based autonomous driving (AD) perception introduces a promising picture for safe and environment-friendly transportation. However, the over-reliance on real labeled data in LiDAR perception limits the scale of on-road…

Unsupervised online 3D instance segmentation is a fundamental yet challenging task, as it requires maintaining consistent object identities across LiDAR scans without relying on annotated training data. Existing methods, such as UNIT, have…