Robust Multi-label Image Classification with Semi-Supervised Learning and Active Learning

In this paper, a novel image classification method, incorporating active learning and semi-supervised learning (SSL), is proposed. In this method, two classifiers are needed where one is trained by labeled data and some unlabeled data, while the other one is trained only by labeled data. Specifically, in each round, two classifiers iterate to select useful examples in contention for user query. Then we compute the label changing rate for every unlabeled example in each classifier. Those examples in which the label changing rate is zero and the label in the two classifiers is the same are selected to add into the training data of the first classifier. Our experimental results show that our method significantly reduced the need of labeled examples, while at the same time reducing classification error compared with widely used image classification algorithms.

Download Full-text

Annotation-efficient classification combining active learning, pre-training and semi-supervised learning for biomedical images

10.1101/2020.12.07.414235 ◽

2020 ◽

Author(s):

Sayedali Shetab Boushehri ◽

Ahmad Bin Qasim ◽

Dominik Waibel ◽

Fabian Schmich ◽

Carsten Marr

Keyword(s):

Active Learning ◽

Image Classification ◽

Supervised Learning ◽

Learning Algorithms ◽

Training Methods ◽

Biomedical Image ◽

Classification Tasks ◽

Training Strategies ◽

Biomedical Image Classification ◽

Image Datasets

AbstractDeep learning image classification algorithms typically require large annotated datasets. In contrast to real world images where labels are typically cheap and easy to get, biomedical applications require experts’ time for annotation, which is often expensive and scarce. Therefore, identifying methods to maximize performance with a minimal amount of annotation is crucial. A number of active learning algorithms address this problem and iteratively identify most informative images for annotation from the data. However, they are mostly benchmarked on natural image datasets and it is not clear how they perform on biomedical image data with strong class imbalance, little color variance and high similarity between classes. Moreover, active learning neglects the typically abundant unlabeled data available.In this paper, we thus explore strategies combining active learning with pre-training and semi-supervised learning to increase performance on biomedical image classification tasks. We first benchmarked three active learning algorithms, three pre-training methods, and two training strategies on a dataset containing almost 20,000 white blood cell images, split up into ten different classes. Both pre-training using self-supervised learning and pre-trained ImageNet weights boosts the performance of active learning algorithms. A further improvement was achieved using semi-supervised learning. An extensive grid-search through the different active learning algorithms, pre-training methods and training strategies on three biomedical image datasets showed that a specific combination of these methods should be used. This recommended strategy improved the results over conventional annotation-efficient classification strategies by 3% to 14% macro recall in every case. We propose this strategy for other biomedical image classification tasks and expect to boost performance whenever scarce annotation is a problem.

Download Full-text