Deeply-supervised nets

Published

Sep 18, 2014

Deeply-supervised nets is an AI model developed by Microsoft Research (United States), first published in September 2014. It works in the vision domain, on tasks such as image classification and digit recognition.

Epoch AI has no training-compute estimate for this model. It was trained on roughly 598.4K datapoints.

The reference paper has 2,509 citations.

Full record

Organization: Microsoft Research
Country of organization: United States
Domain: Vision
Task: Image classification, Digit recognition
Dataset size: 598.4K
Citations: 2,509