English
Related papers

Related papers: Data Efficient 3D Learner via Knowledge Transferre…

200 papers

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

Although well-known large-scale datasets, such as ImageNet, have driven image understanding forward, most of these datasets require extensive manual annotation and are thus not easily scalable. This limits the advancement of image…

Computer Vision and Pattern Recognition · Computer Science 2020-02-07 Jean Lahoud , Bernard Ghanem

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…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Andrew Caunes , Thierry Chateau , Vincent Frémont

The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e.g. point clouds) are notoriously hard. For example, the number of scenes (e.g. indoor rooms) that can be…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Ji Hou , Benjamin Graham , Matthias Nießner , Saining Xie

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…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Mehar Khurana , Neehar Peri , James Hays , Deva Ramanan

Semantic segmentation models only perform well on the domain they are trained on and datasets for training are scarce and often have a small label-spaces, because the pixel level annotations required are expensive to make. Thus training…

Computer Vision and Pattern Recognition · Computer Science 2021-07-12 Floris Naber

Semantic segmentation has emerged as a pivotal area of study in computer vision, offering profound implications for scene understanding and elevating human-machine interactions across various domains. While 2D semantic segmentation has…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Aditya Krishnan , Jayneel Vora , Prasant Mohapatra

Semantic understanding of 3D point cloud relies on learning models with massively annotated data, which, in many cases, are expensive or difficult to collect. This has led to an emerging research interest in semi-supervised learning (SSL)…

Computer Vision and Pattern Recognition · Computer Science 2022-05-03 Xian Shi , Xun Xu , Wanyue Zhang , Xiatian Zhu , Chuan Sheng Foo , Kui Jia

Massive semantically labeled datasets are readily available for 2D images, however, are much harder to achieve for 3D scenes. Objects in 3D repositories like ShapeNet are labeled, but regrettably only in isolation, so without context. 3D…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 David Griffiths , Jan Boehm , Tobias Ritschel

Semantic segmentation of LiDAR point clouds is an important task in autonomous driving. However, training deep models via conventional supervised methods requires large datasets which are costly to label. It is critical to have…

Computer Vision and Pattern Recognition · Computer Science 2022-10-18 Minghua Liu , Yin Zhou , Charles R. Qi , Boqing Gong , Hao Su , Dragomir Anguelov

Traditional supervised medical image segmentation models require large amounts of labeled data for training; however, obtaining such large-scale labeled datasets in the real world is extremely challenging. Recent semi-supervised…

Computer Vision and Pattern Recognition · Computer Science 2025-05-26 Yunyao Lu , Yihang Wu , Reem Kateb , Ahmad Chaddad

Automatic pseudo-labeling is a powerful tool to tap into large amounts of sequential unlabeled data. It is specially appealing in safety-critical applications of autonomous driving, where performance requirements are extreme, datasets are…

Computer Vision and Pattern Recognition · Computer Science 2023-07-06 Awet Haileslassie Gebrehiwot , Patrik Vacek , David Hurych , Karel Zimmermann , Patrick Perez , Tomáš Svoboda

Recently, large-scale pre-trained models such as Segment-Anything Model (SAM) and Contrastive Language-Image Pre-training (CLIP) have demonstrated remarkable success and revolutionized the field of computer vision. These foundation vision…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Shichao Dong , Fayao Liu , Guosheng Lin

In supervised learning, obtaining a large set of fully-labeled training data is expensive. We show that we do not always need full label information on every single training example to train a competent classifier. Specifically, inspired by…

Machine Learning · Computer Science 2023-01-18 Shiyu Duan , Spencer Chang , Jose C. Principe

With the development of 3D and 2D data acquisition techniques, it has become easy to obtain point clouds and images of scenes simultaneously, which further facilitates dual-modal semantic segmentation. Most existing methods for…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Qiulei Dong , Jianan Li , Shuang Deng

Arguably one of the top success stories of deep learning is transfer learning. The finding that pre-training a network on a rich source set (eg., ImageNet) can help boost performance once fine-tuned on a usually much smaller target set, has…

Computer Vision and Pattern Recognition · Computer Science 2020-11-24 Saining Xie , Jiatao Gu , Demi Guo , Charles R. Qi , Leonidas J. Guibas , Or Litany

3D segmentation is a core problem in computer vision and, similarly to many other dense prediction tasks, it requires large amounts of annotated data for adequate training. However, densely labeling 3D point clouds to employ…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Ozan Unal , Christos Sakaridis , Luc Van Gool

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small…

Computer Vision and Pattern Recognition · Computer Science 2017-04-12 Angela Dai , Angel X. Chang , Manolis Savva , Maciej Halber , Thomas Funkhouser , Matthias Nießner

Supervised machine learning based state-of-the-art computer vision techniques are in general data hungry and pose the challenges of not having adequate computing resources and of high costs involved in human labeling efforts. Training data…

Computer Vision and Pattern Recognition · Computer Science 2018-05-30 Vishal Kaushal , Anurag Sahoo , Khoshrav Doctor , Narasimha Raju , Suyash Shetty , Pankaj Singh , Rishabh Iyer , Ganesh Ramakrishnan

Point cloud segmentation is a fundamental task in 3D vision that serves a wide range of applications. Although great progresses have been made these years, its practical usability is still limited by the availability of training data.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Yixun Liang , Hao He , Shishi Xiao , Hao Lu , Yingcong Chen