Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022 |
| Editors | Luc De Raedt, Luc De Raedt |
| Pages | 1298-1305 |
| Number of pages | 8 |
| ISBN (electronic) | 9781956792003 |
| Publication status | Published - 2022 |
| Event | 31st International Joint Conference on Artificial Intelligence, IJCAI 2022 - Vienna, Austria Duration: 23 Jul 2022 → 29 Jul 2022 |
Publication series
| Name | IJCAI International Joint Conference on Artificial Intelligence |
|---|---|
| ISSN (Print) | 1045-0823 |
Abstract
Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of learning deep neural networks on small datasets. Our proposed architecture called ChimeraMix learns a data augmentation by generating compositions of instances. The generative model encodes images in pairs, combines the features guided by a mask, and creates new samples. For evaluation, all methods are trained from scratch without any additional data. Several experiments on benchmark datasets, e.g., ciFAIR-10, STL-10, and ciFAIR-100, demonstrate the superior performance of ChimeraMix compared to current state-of-the-art methods for classification on small datasets. Code is available at https://github.com/creinders/ChimeraMix.
ASJC Scopus subject areas
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022. ed. / Luc De Raedt; Luc De Raedt. 2022. p. 1298-1305 (IJCAI International Joint Conference on Artificial Intelligence).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - ChimeraMix
T2 - 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
AU - Reinders, Christoph
AU - Schubert, Frederik
AU - Rosenhahn, Bodo
N1 - Funding Information: This work was supported by the Federal Ministry of Education and Research (BMBF), Germany, under the project Leib-nizKILabor (grant no. 01DD20003), the Center for Digital Innovations (ZDIN), and the Deutsche Forschungsgemein-schaft (DFG) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122).
PY - 2022
Y1 - 2022
N2 - Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of learning deep neural networks on small datasets. Our proposed architecture called ChimeraMix learns a data augmentation by generating compositions of instances. The generative model encodes images in pairs, combines the features guided by a mask, and creates new samples. For evaluation, all methods are trained from scratch without any additional data. Several experiments on benchmark datasets, e.g., ciFAIR-10, STL-10, and ciFAIR-100, demonstrate the superior performance of ChimeraMix compared to current state-of-the-art methods for classification on small datasets. Code is available at https://github.com/creinders/ChimeraMix.
AB - Deep convolutional neural networks require large amounts of labeled data samples. For many real-world applications, this is a major limitation which is commonly treated by augmentation methods. In this work, we address the problem of learning deep neural networks on small datasets. Our proposed architecture called ChimeraMix learns a data augmentation by generating compositions of instances. The generative model encodes images in pairs, combines the features guided by a mask, and creates new samples. For evaluation, all methods are trained from scratch without any additional data. Several experiments on benchmark datasets, e.g., ciFAIR-10, STL-10, and ciFAIR-100, demonstrate the superior performance of ChimeraMix compared to current state-of-the-art methods for classification on small datasets. Code is available at https://github.com/creinders/ChimeraMix.
UR - http://www.scopus.com/inward/record.url?scp=85137873072&partnerID=8YFLogxK
U2 - 10.24963/ijcai.2022/181
DO - 10.24963/ijcai.2022/181
M3 - Conference contribution
AN - SCOPUS:85137873072
T3 - IJCAI International Joint Conference on Artificial Intelligence
SP - 1298
EP - 1305
BT - Proceedings of the 31st International Joint Conference on Artificial Intelligence, IJCAI 2022
A2 - De Raedt, Luc
A2 - De Raedt, Luc
Y2 - 23 July 2022 through 29 July 2022
ER -