Papers with Code · CC BY-SA 4.0

Domain Generalization

Domain Adaptation › Domain Generalization 596 평가 기록 25 datasets

The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain

<span class="description-source">Source: Diagram Image Retrieval using Sketch-Based Deep Learning and Transfer Learning </span>

논문

Adversarial Training for Free!

1904.12843 2019-04-29 이 페이지의 평가 1건
Accuracy - All Images: 26.7Accuracy - Corrupted Images: 20.5Accuracy - Clean Images: 30.9