Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds

CoRR, 2019.

Cited by: 8|Views148
EI
Weibo:
We show that BADGE is robust to architecture choice, batch size, and dataset, generally performing as well as or better than the best baseline across our experiments, which vary all of the aforementioned environmental conditions

Abstract:

We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of points that are disparate and high-magnitude when represented in a hallucinated gradient space, a strategy designed to incorporate both predictive uncertainty a...More

Code:

Data:

Full Text
Bibtex
Weibo
Your rating :
0

 

Tags
Comments