Active Learning for Multi-class Image Classification
By: Thien Nhan Vo
Potential Business Impact:
Teaches computers to learn with fewer pictures.
A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting examples. Assigning values to image examples using different uncertainty metrics allows the model to identify and select high-value examples in a smaller training set size. We demonstrate results for digit recognition and fruit classification on the MNIST and Fruits360 data sets. We formally compare results for four different uncertainty metrics. Finally, we observe active learning is also effective on simpler (binary) classification tasks, but marked improvement from random sampling is more evident on more difficult tasks. We show active learning is a viable algorithm for image classification problems.
Similar Papers
Active Learning Methods for Efficient Data Utilization and Model Performance Enhancement
Machine Learning (CS)
Teaches computers to learn with less examples.
A model-agnostic active learning approach for animal detection from camera traps
CV and Pattern Recognition
Finds animal pictures faster for conservation.
Active Learning Classification from a Signal Separation Perspective
Machine Learning (CS)
Finds hidden groups in data, even when mixed.