Semi-supervised deep learning by metric embedding

Abstract

Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of their tendency to overfit easily when trained on small amounts of data. In this work we will explore a new training objective that is targeting a semi-supervised regime with only a small subset of labeled data. This criterion is based on a deep metric embedding over distance relations within the set of labeled samples, together with constraints over the embeddings of the unlabeled set. The final learned representations are discriminative in euclidean space, and hence can be used with subsequent nearest-neighbor classification using the labeled samples.

References in corpus (2)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Ensemble Robustness and Generalization of Stochastic Deep Learning Algorithms

Cited by in corpus (9)

• A Review of Semi Supervised Learning Theories and Recent Advances
• Semi-Supervised Learning using Siamese Networks
• Disease-oriented image embedding with pseudo-scanner standardization for content-based image retrieval on 3D brain MRI
• Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning
• Label Prediction Framework for Semi-Supervised Cross-Modal Retrieval
• Efficient feature embedding of 3D brain MRI images for content-based image retrieval with deep metric learning
• Active Crowd Counting with Limited Supervision
• Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression
• Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection