Details
| Original language | English |
|---|---|
| Place of Publication | Düsseldorf |
| Number of pages | 121 |
| ISBN (electronic) | 978-3-18-688910-2 |
| Publication status | Published - 2025 |
Publication series
| Name | Fortschritt-Berichte VDI |
|---|---|
| Volume | Nr. 889 |
| ISSN (Print) | 0341-1796 |
| ISSN (electronic) | 0178-9627 |
Abstract
Keywords
- Image Classification, Object Detection, small data, Bildklassifikation, Training mit wenigen Daten, Random Forests, Objekterkennung, Deep Learning
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Düsseldorf, 2025. 121 p. (Fortschritt-Berichte VDI; Vol. Nr. 889).
Research output: Book/Report › Monograph › Research › peer review
}
TY - BOOK
T1 - Deep learning with very few training examples
AU - Reinders, Christoph
PY - 2025
Y1 - 2025
N2 - This dissertation addresses the problem of training deep learning models with very few training examples. While deep learning has achieved remarkable success across a wide range of domains, deep learning models typically have a vast number of parameters that need to be optimized, and large amounts of labeled data are required for training. However, the collection and annotation of thousands or millions of examples is extremely time-consuming and expensive. This is a significant limitation of deep learning methods in many real-world applications. In the first part, a novel object detection method is proposed for recognizing new categories with very few training examples by combining the advantages of convolutional neural networks and random forests. Subsequently, a new method called Neural Random Forest Imitation (NRFI) is presented, designed to implicitly transform random forests into neural networks. The experiments demonstrate that NRFI is scalable to complex classifiers and generates very small networks. Finally, two novel generative methods, ChimeraMix and HydraMix, are presented for small data image classification, which learn the generation of new image compositions by combining
AB - This dissertation addresses the problem of training deep learning models with very few training examples. While deep learning has achieved remarkable success across a wide range of domains, deep learning models typically have a vast number of parameters that need to be optimized, and large amounts of labeled data are required for training. However, the collection and annotation of thousands or millions of examples is extremely time-consuming and expensive. This is a significant limitation of deep learning methods in many real-world applications. In the first part, a novel object detection method is proposed for recognizing new categories with very few training examples by combining the advantages of convolutional neural networks and random forests. Subsequently, a new method called Neural Random Forest Imitation (NRFI) is presented, designed to implicitly transform random forests into neural networks. The experiments demonstrate that NRFI is scalable to complex classifiers and generates very small networks. Finally, two novel generative methods, ChimeraMix and HydraMix, are presented for small data image classification, which learn the generation of new image compositions by combining
KW - Image Classification
KW - Object Detection
KW - small data
KW - Bildklassifikation
KW - Training mit wenigen Daten
KW - Random Forests
KW - Objekterkennung
KW - Deep Learning
U2 - 10.51202/9783186889102
DO - 10.51202/9783186889102
M3 - Monograph
SN - 9783186889102
T3 - Fortschritt-Berichte VDI
BT - Deep learning with very few training examples
CY - Düsseldorf
ER -