Robust deep learning object recognition models rely on low frequency information in natural images.
Machine learning models have difficulty generalizing to data outside of the distribution they were trained on. In particular, vision models are usually vulnerable to adversarial attacks or common corruptions, to which the human visual system is robust. Recent studies have found that regularizing mac...
שמור ב:
| Principais autores: | , , , , , , , , |
|---|---|
| פורמט: | Artigo |
| שפה: | Inglês |
| יצא לאור: |
Public Library of Science (PLoS)
2023-03-01
|
| סדרה: | PLoS Computational Biology |
| גישה מקוונת: | https://doi.org/10.1371/journal.pcbi.1010932 |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|