The Truth is Out There : Focusing on Smaller to Guess Bigger in Image Classification
Terziyan, V., Kaikova, O., Malyk, D., & Branytskyi, V. (2023). The Truth is Out There : Focusing on Smaller to Guess Bigger in Image Classification. In F. Longo, M. Affenzeller, A. Padovano, & S. Weiming (Eds.), 4th International Conference on Industry 4.0 and Smart Manufacturing (217, pp. 1323-1334). Elsevier. Procedia Computer Science. https://doi.org/10.1016/j.procs.2022.12.330
Julkaistu sarjassa
Procedia Computer SciencePäivämäärä
2023Tekijänoikeudet
© 2022 The Authors. Published by Elsevier B.V.
2023:92 | 2024:54 | 2025:1
In Artificial Intelligence (AI) in general and in Machine Learning (ML) in particular, which are important and integral components of modern Industry 4.0, we often deal with uncertainty, e.g., lack of complete information about the objects we are classifying, recognizing, diagnosing, etc. Traditionally, uncertainty is considered to be a problem especially in the responsible use of AI and ML tools in the smart manufacturing domain. However, in this study, we aim not to fight with but rather to benefit from the uncertainty to improve the classification performance in supervised ML. Our objective is a kind of uncertainty-driven technique to improve the performance of Convolutional Neural Networks (CNNs) for image classification. The intuition behind our suggested “decontextualize-and-extrapolate” approach is as follows: any image not necessarily contains all the needed information for perfect classification; any trained CNN will give for the entire image (with some uncertainty) the probability distribution among possible classes; the same CNN may also give similar probability distribution to the “part” of the image (i.e., with the higher uncertainty); one may discover the trend of the probability distribution change with the change of uncertainty value; a better (refined) probability distribution could be computed from these two distributions as the result of their extrapolation towards the less uncertainty. In this paper, we suggested several ways and corresponding analytics to discover reasonable part(s) of the images and to make the extrapolation to get better (refined) image classification results. We have considered image representation at the level of pixels as well as at the level of the discovered features. Our preliminary experiments show that the suggested refinement techniques (applied during the testing phase of the CNNs) can improve their classification performance.
See presentation slides: https://ai.it.jyu.fi/ISM-2022-Uncertainty.pptx
...
Julkaisija
ElsevierKonferenssi
International Conference on Industry 4.0 and Smart ManufacturingKuuluu julkaisuun
4th International Conference on Industry 4.0 and Smart ManufacturingISSN Hae Julkaisufoorumista
1877-0509Asiasanat
Julkaisu tutkimustietojärjestelmässä
https://converis.jyu.fi/converis/portal/detail/Publication/172577863
Metadata
Näytä kaikki kuvailutiedotKokoelmat
Lisenssi
Samankaltainen aineisto
Näytetään aineistoja, joilla on samankaltainen nimeke tai asiasanat.
-
Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance
Xu, Qi; Zhou, Dongdong; Wang, Jian; Shen, Jiangrong; Kettunen, Lauri; Cong, Fengyu (IEEE, 2022)Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class ... -
Causality-Aware Convolutional Neural Networks for Advanced Image Classification and Generation
Terziyan, Vagan; Vitko, Oleksandra (Elsevier, 2023)Smart manufacturing uses emerging deep learning models, and particularly Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), for different industrial diagnostics tasks, e.g., classification, ... -
Hyper-flexible Convolutional Neural Networks based on Generalized Lehmer and Power Means
Terziyan, Vagan; Malyk, Diana; Golovianko, Mariia; Branytskyi, Vladyslav (Elsevier, 2022)Convolutional Neural Network is one of the famous members of the deep learning family of neural network architectures, which is used for many purposes, including image classification. In spite of the wide adoption, such ... -
Tree species classification of drone hyperspectral and RGB imagery with deep learning convolutional neural networks
Nezami, Somayeh; Khoramshahi, Ehsan; Nevalainen, Olli; Pölönen, Ilkka; Honkavaara, Eija (MDPI AG, 2020)Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include ... -
Automatic image‐based identification and biomass estimation of invertebrates
Ärje, Johanna; Melvad, Claus; Jeppesen, Mads Rosenhøj; Madsen, Sigurd Agerskov; Raitoharju, Jenni; Rasmussen, Maria Strandgård; Iosifidis, Alexandros; Tirronen, Ville; Gabbouj, Moncef; Meissner, Kristian; Høye, Toke Thomas (Wiley, 2020)Understanding how biological communities respond to environmental changes is a key challenge in ecology and ecosystem management. The apparent decline of insect populations necessitates more biomonitoring but the time-consuming ...
Ellei toisin mainittu, julkisesti saatavilla olevia JYX-metatietoja (poislukien tiivistelmät) saa vapaasti uudelleenkäyttää CC0-lisenssillä.