Curriculum Learning with Diversity for Supervised Computer Vision Tasks

Abstract

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. We consider this kind of difficulty metric to be better suited for solving general problems, as it is not based on certain task-dependent elements, but more on the context of each image. We ensure the diversity during training, giving higher priority to elements from less visited classes. We conduct object detection and instance segmentation experiments on Pascal VOC 2007 and Cityscapes data sets, surpassing both the randomly-trained baseline and the standard curriculum approach. We prove that our strategy is very efficient for unbalanced data sets, leading to faster convergence and more accurate results, when other curriculum-based strategies fail.

arXiv commentAccepted at MRC 2020 @ ECAI

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• On The Power of Curriculum Learning in Training Deep Networks
• Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
• Self Paced Deep Learning for Weakly Supervised Object Detection
• An Empirical Exploration of Curriculum Learning for Neural Machine Translation
• Adversarial Generation of Natural Language
• Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation