Using mixup as a regularizer can surprisingly improve accuracy and out-of-distribution robustness

Using mixup as a regularizer can surprisingly improve accuracy and out-of-distribution robustness

We show that the effectiveness of the well celebrated Mixup can be further improved if instead of using it as the sole learning objective, it is utilized as an additional regularizer to the standard cross-entropy loss. This simple change not only improves accuracy but also significantly improves the...

Volledige beschrijving

Bibliografische gegevens
Hoofdauteurs: Pinto, F, Yang, H, Lim, SN, Torr, PHS, Dokania, PK
Formaat: Conference item
Taal:English
Gepubliceerd in: Curran Associates, Inc 2023

Gelijkaardige items

Gelijkaardige items