English
Related papers

Related papers: Training Deep Networks with Synthetic Data: Bridgi…

200 papers

A major challenges of deep learning (DL) is the necessity to collect huge amounts of training data. Often, the lack of a sufficiently large dataset discourages the use of DL in certain applications. Typically, acquiring the required amounts…

Computer Vision and Pattern Recognition · Computer Science 2024-10-31 Andoni Cortés , Clemente Rodríguez , Gorka Velez , Javier Barandiarán , Marcos Nieto

Deep learning has rapidly transformed the state of the art algorithms used to address a variety of problems in computer vision and robotics. These breakthroughs have relied upon massive amounts of human annotated training data. This time…

Computer Vision and Pattern Recognition · Computer Science 2017-02-28 Matthew Johnson-Roberson , Charles Barto , Rounak Mehta , Sharath Nittur Sridhar , Karl Rosaen , Ram Vasudevan

Deep learning methods typically require vast amounts of training data to reach their full potential. While some publicly available datasets exists, domain specific data always needs to be collected and manually labeled, an expensive, time…

Computer Vision and Pattern Recognition · Computer Science 2019-02-27 Stefan Hinterstoisser , Olivier Pauly , Hauke Heibel , Martina Marek , Martin Bokeloh

A number of studies have investigated the training of neural networks with synthetic data for applications in the real world. The aim of this study is to quantify how much real world data can be saved when using a mixed dataset of synthetic…

Computer Vision and Pattern Recognition · Computer Science 2022-02-02 Sven Burdorf , Karoline Plum , Daniel Hasenklever

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for…

Robotics · Computer Science 2022-10-26 Dániel Horváth , Gábor Erdős , Zoltán Istenes , Tomáš Horváth , Sándor Földi

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

Synthetic data is a scalable alternative to manual supervision, but it requires overcoming the sim-to-real domain gap. This discrepancy between virtual and real worlds is addressed by two seemingly opposed approaches: improving the realism…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Sergey Zakharov , Rares Ambrus , Vitor Guizilini , Wadim Kehl , Adrien Gaidon

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

Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute…

Image and Video Processing · Electrical Eng. & Systems 2025-12-08 Malte Hoffmann

In recent years, deep learning models have resulted in a huge amount of progress in various areas, including computer vision. By nature, the supervised training of deep models requires a large amount of data to be available. This ideal case…

Computer Vision and Pattern Recognition · Computer Science 2019-07-17 Farzan Erlik Nowruzi , Prince Kapoor , Dhanvin Kolhatkar , Fahed Al Hassanat , Robert Laganiere , Julien Rebut

Data-driven depth estimation methods struggle with the generalization outside their training scenes due to the immense variability of the real-world scenes. This problem can be partially addressed by utilising synthetically generated…

Computer Vision and Pattern Recognition · Computer Science 2020-05-20 Maxim Maximov , Kevin Galim , Laura Leal-Taixé

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-11 Xiangyu Yue , Yang Zhang , Sicheng Zhao , Alberto Sangiovanni-Vincentelli , Kurt Keutzer , Boqing Gong

Deep neural networks have largely failed to effectively utilize synthetic data when applied to real images due to the covariate shift problem. In this paper, we show that by applying a straightforward modification to an existing…

Computer Vision and Pattern Recognition · Computer Science 2018-07-26 Aysegul Dundar , Ming-Yu Liu , Ting-Chun Wang , John Zedlewski , Jan Kautz

While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their training. It thus became common to use available synthetic…

Computer Vision and Pattern Recognition · Computer Science 2018-10-10 Benjamin Planche , Sergey Zakharov , Ziyan Wu , Andreas Hutter , Harald Kosch , Slobodan Ilic

Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and…

Computer Vision and Pattern Recognition · Computer Science 2018-10-03 Alexandra Carlson , Katherine A. Skinner , Ram Vasudevan , Matthew Johnson-Roberson

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Xiaoling Hu , Xiangrui Zeng , Oula Puonti , Juan Eugenio Iglesias , Bruce Fischl , Yael Balbastre

We present a method for synthesizing naturally looking images of multiple people interacting in a specific scenario. These images benefit from the advantages of synthetic data: being fully controllable and fully annotated with any type of…

Computer Vision and Pattern Recognition · Computer Science 2020-06-04 Igor Kviatkovsky , Nadav Bhonker , Gerard Medioni

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…

Computer Vision and Pattern Recognition · Computer Science 2017-07-04 Yinda Zhang , Shuran Song , Ersin Yumer , Manolis Savva , Joon-Young Lee , Hailin Jin , Thomas Funkhouser

In human learning, it is common to use multiple sources of information jointly. However, most existing feature learning approaches learn from only a single task. In this paper, we propose a novel multi-task deep network to learn…

Computer Vision and Pattern Recognition · Computer Science 2017-11-27 Zhongzheng Ren , Yong Jae Lee

Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required for good performance.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-18 Frederik Hagelskjaer , Anders Glent Buch