Top 1 Accuracy: 64.3
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
mean Corruption Error (mCE): 51.3Top 1 Accuracy: 59.9
mean Corruption Error (mCE): 46.8
Top 1 Accuracy: 56.5
mean Corruption Error (mCE): 57.5
mean Corruption Error (mCE): 65.3
mean Corruption Error (mCE): 76.7
Average Accuracy: 85.5
mean Corruption Error (mCE): 54.4Number of params: 21M
Average Accuracy: 83.1
Average Accuracy: 82.9
mean Corruption Error (mCE): 53.8
mean Corruption Error (mCE): 69.6
mean Corruption Error (mCE): 69.3
Average Accuracy: 83.25
mean Corruption Error (mCE): 49.95Top 1 Accuracy: 69.4Number of params: 25.6
mean Corruption Error (mCE): 50.6
mean Corruption Error (mCE): 48.9
Average Accuracy: 84.0
mean Corruption Error (mCE): 60.4
Average Accuracy: 84.5