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...
I tiakina i:
| Ngā kaituhi matua: | , , , , , , , , |
|---|---|
| Hōputu: | Artigo |
| Reo: | Inglês |
| I whakaputaina: |
Public Library of Science (PLoS)
2023-03-01
|
| Rangatū: | PLoS Computational Biology |
| Urunga tuihono: | https://doi.org/10.1371/journal.pcbi.1010932 |
| Ngā Tūtohu: |
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|