English
Related papers

Related papers: Training Deep Learning Models with Hybrid Datasets…

200 papers

One of the grand challenges of deep learning is the requirement to obtain large labeled training data sets. While synthesized data sets can be used to overcome this challenge, it is important that these data sets close the reality gap,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Sebastian Hartwig , Timo Ropinski

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

Computer Vision and Pattern Recognition · Computer Science 2018-04-25 Jonathan Tremblay , Aayush Prakash , David Acuna , Mark Brophy , Varun Jampani , Cem Anil , Thang To , Eric Cameracci , Shaad Boochoon , Stan Birchfield

Leveraging synthetically rendered data offers great potential to improve monocular depth estimation and other geometric estimation tasks, but closing the synthetic-real domain gap is a non-trivial and important task. While much recent work…

Computer Vision and Pattern Recognition · Computer Science 2020-06-26 Yunhan Zhao , Shu Kong , Daeyun Shin , Charless Fowlkes

Deep vision models are now mature enough to be integrated in industrial and possibly critical applications such as autonomous navigation. Yet, data collection and labeling to train such models requires too much efforts and costs for a…

Machine Learning · Computer Science 2025-10-24 Estelle Chigot , Dennis G. Wilson , Meriem Ghrib , Fabrice Jimenez , Thomas Oberlin

In this thesis, we leverage monocular cameras on aerial robots to predict depth and semantic maps in low-altitude unstructured environments. We propose a joint deep-learning architecture, named Co-SemDepth, that can perform the two tasks…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Yara AlaaEldin

Selective weeding is one of the key challenges in the field of agriculture robotics. To accomplish this task, a farm robot should be able to accurately detect plants and to distinguish them between crop and weeds. Most of the promising…

Computer Vision and Pattern Recognition · Computer Science 2017-12-19 Maurilio Di Cicco , Ciro Potena , Giorgio Grisetti , Alberto Pretto

Using synthetic data for training deep neural networks for robotic manipulation holds the promise of an almost unlimited amount of pre-labeled training data, generated safely out of harm's way. One of the key challenges of synthetic data,…

Robotics · Computer Science 2018-10-01 Jonathan Tremblay , Thang To , Balakumar Sundaralingam , Yu Xiang , Dieter Fox , Stan Birchfield

Deep Learning methods usually require huge amounts of training data to perform at their full potential, and often require expensive manual labeling. Using synthetic images is therefore very attractive to train object detectors, as the…

Computer Vision and Pattern Recognition · Computer Science 2017-11-20 Stefan Hinterstoisser , Vincent Lepetit , Paul Wohlhart , Kurt Konolige

Face Presentation Attack Detection (PAD) plays a pivotal role in securing face recognition systems against spoofing attacks. Although great progress has been made in designing face PAD methods, developing a model that can generalize well to…

Computer Vision and Pattern Recognition · Computer Science 2023-09-19 Usman Muhammad , Jorma Laaksonen , Djamila Romaissa Beddiar , Mourad Oussalah

Precise semantic segmentation of crops and weeds is necessary for agricultural weeding robots. However, training deep learning models requires large annotated datasets, which are costly to obtain in real fields. Synthetic data can reduce…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Garen Boyadjian , Cyrille Pierre , Johann Laconte , Riccardo Bertoglio

Data collection has always been a major issue in the modeling and training of large deep learning networks, as no dataset can account for every slight deviation we might see in live usage. Collecting samples can be especially costly for…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Conor Flynn , Christopher Ebersole , Edmund Zelnio

Semantic image segmentation is a central and challenging task in autonomous driving, addressed by training deep models. Since this training draws to a curse of human-based image labeling, using synthetic images with automatically generated…

Computer Vision and Pattern Recognition · Computer Science 2023-01-31 Jose L. Gómez , Gabriel Villalonga , Antonio M. López

The growing number of pretrained models in Machine Learning (ML) presents significant challenges for practitioners. Given a new dataset, they need to determine the most suitable deep learning (DL) pipeline, consisting of the pretrained…

Machine Learning · Computer Science 2025-06-17 Fabio Ferreira

Intrinsic image decomposition is the process of separating the reflectance and shading layers of an image, which is a challenging and underdetermined problem. In this paper, we propose to systematically address this problem using a deep…

Computer Vision and Pattern Recognition · Computer Science 2018-07-31 Sai Bi , Nima Khademi Kalantari , Ravi Ramamoorthi

Recently, the use of synthetic training data has been on the rise as it offers correctly labelled datasets at a lower cost. The downside of this technique is that the so-called domain gap between the real target images and synthetic…

Computer Vision and Pattern Recognition · Computer Science 2022-11-30 Bram Vanherle , Steven Moonen , Frank Van Reeth , Nick Michiels

Deep learning is expected to offer new opportunities and a new paradigm for the field of architecture. One such opportunity is teaching neural networks to visually understand architectural elements from the built environment. However, the…

Machine Learning · Computer Science 2021-05-11 Mohammad Alawadhi , Wei Yan

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…

Computer Vision and Pattern Recognition · Computer Science 2021-07-23 Pierre Gutierrez , Maria Luschkova , Antoine Cordier , Mustafa Shukor , Mona Schappert , Tim Dahmen

Drone detection has benefited from improvements in deep neural networks, but like many other applications, suffers from the availability of accurate data for training. Synthetic data provides a potential for low-cost data generation and has…

Computer Vision and Pattern Recognition · Computer Science 2024-11-15 Mariusz Wisniewski , Zeeshan A. Rana , Ivan Petrunin , Alan Holt , Stephen Harman

With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images. However, discrepancies with the real data acquired from various…

Computer Vision and Pattern Recognition · Computer Science 2018-05-25 Sergey Zakharov , Benjamin Planche , Ziyan Wu , Andreas Hutter , Harald Kosch , Slobodan Ilic

Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation…

Computer Vision and Pattern Recognition · Computer Science 2020-04-28 Dawei Yang , Jia Deng