Deep Active Learning for Biased Datasets via Fisher Kernel\n Self-Supervision

2020/02/29 by Denis Gudovskiy, Alec Hodgkinson, Gudovskiy, Denis +5 · 2 citations
Computer Science · #Machine Learning and Algorithms #Machine Learning and Data Classification #Domain Adaptation and Few-Shot Learning

paper · pdf · doi:10.48550/arxiv.2003.00393

Abstract

Active learning (AL) aims to minimize labeling efforts for data-demanding\ndeep neural networks (DNNs) by selecting the most representative data points\nfor annotation. However, currently used methods are ill-equipped to deal with\nbiased data. The main motivation of this paper is to consider a realistic\nsetting for pool-based semi-supervised AL, where the unlabeled collection of\ntrain data is biased. We theoretically derive an optimal acquisition function\nfor AL in this setting. It can be formulated as distribution shift minimization\nbetween unlabeled train data and weakly-labeled validation dataset. To\nimplement such acquisition function, we propose a low-complexity method for\nfeature density matching using self-supervised Fisher kernel (FK) as well as\nseveral novel pseudo-label estimators. Our FK-based method outperforms\nstate-of-the-art methods on MNIST, SVHN, and ImageNet classification while\nrequiring only 1/10th of processing. The conducted experiments show at least\n40% drop in labeling efforts for the biased class-imbalanced data compared to\nexisting methods.\n

Cited by

• PGTuner: An Efficient Framework for Automatic and Transferable Configuration Tuning of Proximity Graphs
• Exploring Active Learning for Semiconductor Defect Segmentation

Related

• Active Learning at the ImageNet Scale
• Deep Bayesian Active Semi-Supervised Learning
• A Neural Pre-Conditioning Active Learning Algorithm to Reduce Label Complexity
• PAL : Pretext-based Active Learning
• Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost