Sign in

Deep Active Learning by Model Interpretability

By Qiang Liu and others
Recent successes of Deep Neural Networks (DNNs) in a variety of research tasks, however, heavily rely on the large amounts of labeled samples. This may require considerable annotation cost in real-world applications. Fortunately, active learning is a promising methodology to train high-performing model with minimal annotation cost. In the deep... Show more
August 18, 2020
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Deep Active Learning by Model Interpretability
Click on play to start listening