Top-1 accuracy: 54.5
Papers with Code · CC BY-SA 4.0
Domain Generalization
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
Accuracy - All Images: 23.1Accuracy - Corrupted Images: 17.5Accuracy - Clean Images: 26.8
Top-1 accuracy: 65.5
Top-1 accuracy: 77.18
Top-1 accuracy: 46.03
Top-1 accuracy: 55.0
Top-1 accuracy: 53.39
Accuracy - Clean Images: 450
Top-1 accuracy: 44.72
Top-1 accuracy: 46.1
Average Accuracy: 64.3
Top-1 accuracy: 50.03
Average Accuracy: 61.1
Top-1 accuracy: 48.3
Accuracy - All Images: 25.3Accuracy - Corrupted Images: 20.4Accuracy - Clean Images: 30
Top-1 accuracy: 50.9
Average Accuracy: 65
Top-1 accuracy: 35.8
Average Accuracy: 69.6
Top-1 accuracy: 45.6