English
Related papers

Related papers: You Never Get a Second Chance To Make a Good First…

200 papers

Learning semantic segmentation requires pixel-wise annotations, which can be time-consuming and expensive. To reduce the annotation cost, we propose a superpixel-based active learning (AL) framework, which collects a dominant label per…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Hoyoung Kim , Minhyeon Oh , Sehyun Hwang , Suha Kwak , Jungseul Ok

One of the biggest challenges that complicates applied supervised machine learning is the need for huge amounts of labeled data. Active Learning (AL) is a well-known standard method for efficiently obtaining labeled data by first labeling…

Machine Learning · Computer Science 2021-08-18 Julius Gonsior , Maik Thiele , Wolfgang Lehner

We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable…

Computer Vision and Pattern Recognition · Computer Science 2020-03-20 Yawar Siddiqui , Julien Valentin , Matthias Nießner

Active learning selects the most informative samples to exploit limited annotation budgets. Existing work follows a cumbersome pipeline that repeats the time-consuming model training and batch data selection multiple times. In this paper,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Yichen Xie , Masayoshi Tomizuka , Wei Zhan

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…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Ozan Unal , Dengxin Dai , Ali Tamer Unal , Luc Van Gool

Deep learning has seen remarkable advancements in machine learning, yet it often demands extensive annotated data. Tasks like 3D semantic segmentation impose a substantial annotation burden, especially in domains like medicine, where expert…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Arvind Murari Vepa , Zukang Yang , Andrew Choi , Jungseock Joo , Fabien Scalzo , Yizhou Sun

Semantic segmentation is a complex task that relies heavily on large amounts of annotated image data. However, annotating such data can be time-consuming and resource-intensive, especially in the medical domain. Active Learning (AL) is a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Fei Wu , Pablo Marquez-Neila , Mingyi Zheng , Hedyeh Rafii-Tari , Raphael Sznitman

We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-based sample selection.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Chenxi Li , Nuo Chen , Fengyun Tan , Yantong Chen , Bochun Yuan , Tianrui Li , Chongshou Li

Active learning is considered a viable solution to alleviate the contradiction between the high dependency of deep learning-based segmentation methods on annotated data and the expensive pixel-level annotation cost of medical images.…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Jun Shi , Shulan Ruan , Ziqi Zhu , Minfan Zhao , Hong An , Xudong Xue , Bing Yan

Image annotation is one of the most essential tasks for guaranteeing proper treatment for patients and tracking progress over the course of therapy in the field of medical imaging and disease diagnosis. However, manually annotating a lot of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-25 Md Abdul Kadir , Hasan Md Tusfiqur Alam , Pascale Maul , Hans-Jürgen Profitlich , Moritz Wolf , Daniel Sonntag

Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene. However, such strong supervision suffers from large annotation…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 An Tao , Yueqi Duan , Yi Wei , Jiwen Lu , Jie Zhou

We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and…

Computer Vision and Pattern Recognition · Computer Science 2021-07-07 Qingyong Hu , Bo Yang , Linhai Xie , Stefano Rosa , Yulan Guo , Zhihua Wang , Niki Trigoni , Andrew Markham

Obtaining human per-pixel labels for semantic segmentation is incredibly laborious, often making labeled dataset construction prohibitively expensive. Here, we endeavor to overcome this problem with a novel algorithm that combines…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Aneesh Rangnekar , Christopher Kanan , Matthew Hoffman

Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels,…

Computer Vision and Pattern Recognition · Computer Science 2021-11-24 Zhengzhe Liu , Xiaojuan Qi , Chi-Wing Fu

Active learning, a label-efficient paradigm, empowers models to interactively query an oracle for labeling new data. In the realm of LiDAR semantic segmentation, the challenges stem from the sheer volume of point clouds, rendering…

Computer Vision and Pattern Recognition · Computer Science 2023-11-01 Binhui Xie , Shuang Li , Qingju Guo , Chi Harold Liu , Xinjing Cheng

Federated learning (FL) has been intensively investigated in terms of communication efficiency, privacy, and fairness. However, efficient annotation, which is a pain point in real-world FL applications, is less studied. In this project, we…

Machine Learning · Computer Science 2024-03-19 Jin-Hyun Ahn , Kyungsang Kim , Jeongwan Koh , Quanzheng Li

Understanding 3D point cloud models for learning purposes has become an imperative challenge for real-world identification such as autonomous driving systems. A wide variety of solutions using deep learning have been proposed for point…

Computer Vision and Pattern Recognition · Computer Science 2022-06-01 Farid Ghareh Mohammadi , Cheng Chen , Farzan Shenavarmasouleh , M. Hadi Amini , Beshoy Morkos , Hamid R. Arabnia

Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus,…

Computer Vision and Pattern Recognition · Computer Science 2021-05-06 Puzuo Wang , Wei Yao

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

Computer Vision and Pattern Recognition · Computer Science 2020-08-27 Xin Kong , Guangyao Zhai , Baoquan Zhong , Yong Liu

Impressive performance on point cloud semantic segmentation has been achieved by fully-supervised methods with large amounts of labelled data. As it is labour-intensive to acquire large-scale point cloud data with point-wise labels, many…

Computer Vision and Pattern Recognition · Computer Science 2023-08-23 Zongyi Xu , Bo Yuan , Shanshan Zhao , Qianni Zhang , Xinbo Gao