Curriculum Learning with Diversity for Supervised Computer Vision Tasks

Understand

Curriculum learning techniques are a viable solution for improving the accuracy of automatic models, by replacing the traditional random training with an easy-to-hard strategy.

• However, the standard curriculum methodology does not automatically provide improved results, but it is constrained by multiple elements like the data distribution or the proposed model.
• In this paper, we introduce a novel curriculum sampling strategy which takes into consideration the diversity of the training data together with the difficulty of the inputs.
• We determine the difficulty using a state-of-the-art estimator based on the human time required for solving a visual search task.