Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization

Abstract

Recent findings have shown that highly over-parameterized Neural Networks generalize without pretraining or explicit regularization. It is achieved with zero training error, i.e., complete over-fitting by memorizing the training data. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that a randomly initialized VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.
Original languageGerman
Pages279 - 283
Number of pages5
DOIs
Publication statusPublished - 15.02.2023
Event15th International Conference on Machine Learning and Computing - Zhuhai, China
Duration: 17.02.202320.02.2023
Conference number: 192850
https://www.icmlc.org

Conference

Conference15th International Conference on Machine Learning and Computing
Abbreviated titleICMLC 2023
Country/TerritoryChina
CityZhuhai
Period17.02.2320.02.23
Internet address

Research Areas and Centers

  • Centers: Center for Artificial Intelligence Luebeck (ZKIL)

Cite this