Reliable Deep Learning for Machine Vision

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 1373

Special Issue Editor

Department of Mathematics and Computer Science, University of Southern Denmark, 5230 Odense, Denmark
Interests: Bayesian deep learning; neural stochastic processes; uncertainty quantification
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Deep neural nets have been observed to push the state of the art significantly forward in prediction tasks when sufficient data, a well-behaved loss function, and sufficient computational resources are provided. Safety-critical or cost-sensitive applications such as medical diagnostics, autonomous driving, and computer-assisted surgery necessitate reliable assessment of prediction risk. To date, neural networks cannot deliver uncertainty scores reliable enough to be used as a building block in safety-critical real-world applications. This Special Issue aims to raise awareness of the scientific community to the critical role of model reliability in making deep neural nets applicable to many of the future technologies. The Issue welcomes original research papers in areas including but not limited to:

  • Neural network calibration methods
  • Probabilistic approaches to deep learning
  • Approximate Bayesian neural network inference
  • Explainable deep learning
  • Deep generative networks
  • Deep learning for medical diagnostics
  • Deep learning for autonomous mobility
  • Deep learning for computer-assisted surgery

Dr. Melih Kandemir
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • uncertainty quantification
  • uncertainty calibration
  • Bayesian deep learning
  • probabilistic machine learning

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 10869 KiB  
Article
ALReg: Registration of 3D Point Clouds Using Active Learning
by Yusuf Huseyin Sahin, Oguzhan Karabacak, Melih Kandemir and Gozde Unal
Appl. Sci. 2023, 13(13), 7422; https://doi.org/10.3390/app13137422 - 22 Jun 2023
Cited by 1 | Viewed by 969
Abstract
After the success of deep learning in point cloud segmentation and classification tasks, it has also been adopted as common practice in point cloud registration applications. State-of-the-art point cloud registration methods generally deal with this problem as a regression task to find the [...] Read more.
After the success of deep learning in point cloud segmentation and classification tasks, it has also been adopted as common practice in point cloud registration applications. State-of-the-art point cloud registration methods generally deal with this problem as a regression task to find the underlying rotation and translation between two point clouds. However, given two point clouds, the transformation between them could be calculated using only definitive point subsets from each cloud. Furthermore, training time is still a major problem among the current registration networks, whereas using a selective approach to define the informative point subsets can lead to reduced network training times. To that end, we developed ALReg, an active learning procedure to select a limited subset of point clouds to train the network. Each of the point clouds in the training set is divided into superpoints (small pieces of each cloud) and the training process is started with a small amount of them. By actively selecting new superpoints and including them in the training process, only a prescribed amount of data is used, hence the time needed to converge drastically decreases. We used DeepBBS, FMR, and DCP methods as our baselines to prove our proposed ALReg method. We trained DeepBBS and DCP on the ModelNet40 dataset and FMR on the 7Scenes dataset. Using 25% of the training data for ModelNet and 4% for the 7Scenes, better or similar accuracy scores are obtained in less than 20% of their original training times. The trained models are also tested on the 3DMatch dataset and better results are obtained than the original FMR training procedure. Full article
(This article belongs to the Special Issue Reliable Deep Learning for Machine Vision)
Show Figures

Figure 1

Back to TopTop