Semi-supervised Learning Using Siamese Networks

Abstract

Neural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully for semi-supervised problems where small amounts of labeled instances are available along with a large number of unlabeled instances. This work explores a new training method for semi-supervised learning that is based on similarity function learning using a Siamese network to obtain a suitable embedding. The learned representations are discriminative in Euclidean space, and hence can be used for labeling unlabeled instances using a nearest-neighbor classifier. Confident predictions of unlabeled instances are used as true labels for retraining the Siamese network on the expanded training set. This process is applied iteratively. We perform an empirical study of this iterative self-training algorithm. For improving unlabeled predictions, local learning with global consisten

Stats

• citations9
• S2 citations—
• github stars0
• HF likes0
• heat score7.50
• arxiv keysahito2021semi

Related papers

• Deep Learning Based Face Recognition Method Using Siamese Network (2023)0.00
• Semi-supervised Deep Learning By Metric Embedding (2016)0.00
• Local Feature Descriptor Learning With Adaptive Siamese Network (2017)0.00
• Retrieval Of Family Members Using Siamese Neural Network (2020)7.81
• Learning To Learn In A Semi-supervised Fashion (2020)2.26
• An Experimental Evaluation Of Siamese Neural Networks For Robot Localization Using Omnidirectional Imaging In Indoor Environments (2024)6.34
• Image Retrieval And Pattern Spotting Using Siamese Neural Network (2019)11.58
• Metric Learning By Similarity Network For Deep Semi-supervised Learning (2020)3.58