mixup: Beyond Empirical Risk Minimization
Abstrak
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple linear behavior in-between training examples. Our experiments on the ImageNet-2012, CIFAR-10, CIFAR-100, Google commands and UCI datasets show that mixup improves the generalization of state-of-the-art neural network architectures. We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.
Topik & Kata Kunci
Penulis (4)
Hongyi Zhang
Moustapha Cissé
Yann Dauphin
David Lopez-Paz
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2017
- Bahasa
- en
- Total Sitasi
- 11536×
- Sumber Database
- Semantic Scholar
- Akses
- Open Access ✓