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 language | German |
---|---|
Pages | 279 - 283 |
Number of pages | 5 |
DOIs | |
Publication status | Published - 15.02.2023 |
Event | 15th International Conference on Machine Learning and Computing - Zhuhai, China Duration: 17.02.2023 → 20.02.2023 Conference number: 192850 https://www.icmlc.org |
Conference
Conference | 15th International Conference on Machine Learning and Computing |
---|---|
Abbreviated title | ICMLC 2023 |
Country/Territory | China |
City | Zhuhai |
Period | 17.02.23 → 20.02.23 |
Internet address |
Research Areas and Centers
- Centers: Center for Artificial Intelligence Luebeck (ZKIL)