Learning to Segment Generic Handheld Objects Using Class-Agnostic Deep Comparison and Segmentation Network
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2018.2856917
Abstract: Learning unknown objects in the environment is important for detection and manipulation tasks. Prior to learning the unknown objects the ground-truth labels have to be provided. The data annotation or labeling can be achieved in… read more here.
Keywords: network; handheld objects; deep comparison; class agnostic ... See more keywords
Unsupervised Class-Agnostic Instance Segmentation of 3D LiDAR Data for Autonomous Vehicles
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2022.3187872
Abstract: Fine-grained scene understanding is essential for autonomous driving. The context around a vehicle can change drastically while navigating, making it hard to identify and understand the different objects that may appear. Although recent efforts on… read more here.
Keywords: segmentation; class agnostic; instance segmentation; agnostic instance ... See more keywords
Configurable Embodied Data Generation for Class-Agnostic RGB-D Video Segmentation
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Robotics and Automation Letters"
DOI: 10.1109/lra.2024.3486213
Abstract: This letter presents a method for generating large-scale datasets to improve class-agnostic video segmentation across robots with different form factors. Specifically, we consider the question of whether video segmentation models trained on generic segmentation data… read more here.
Keywords: segmentation; class agnostic; data generation; rgb video ... See more keywords
Weakly and Self-Supervised Class-Agnostic Motion Prediction for Autonomous Driving
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2025.3604036
Abstract: 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 LiDAR point clouds. Outdoor scenes typically… read more here.
Keywords: self supervised; agnostic motion; class agnostic; motion prediction ... See more keywords