Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank

Abstract

For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, but related to the supervised task) for which data is abundantly available. In this paper, we show how ranking can be used as a proxy task for some regression problems. As another contribution, we propose an efficient backpropagation technique for Siamese networks which prevents the redundant computation introduced by the multi-branch network architecture. We apply our framework to two regression problems: Image Quality Assessment (IQA) and Crowd Counting. For both we show how to automatically generate ranked image sets from unlabeled data. Our results show that networks trained to regress to the ground truth targets for labeled data and to simultaneously learn to rank unlabeled data obtain significantly better, state-of-the-art results for both IQA and crowd counting. In addition, we show that measuring network uncertainty on the self-supervised proxy task is a good measure of informativeness of unlabeled data. This can be used to drive an algorithm for active learning and we show that this reduces labeling effort by up to 50%.

Accepted at TPAMI. (Keywords: Learning from rankings, image quality assessment, crowd counting, active learning). arXiv admin note: text overlap with arXiv:1803.03095

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs
• CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
• Crowd Counting by Adapting Convolutional Neural Networks with Side Information

Cited by in corpus (1)

• Controlling biases and diversity in diverse image-to-image translation