Beyond Learning Features: Training a Fully-Functional Classifier with ZERO Instance-Level Labels

Citations Over Time

Abstract

We attempt to train deep neural networks for classification without using any labeled data. Existing unsupervised methods, though mine useful clusters or features, require some annotated samples to facilitate the final task-specific predictions. This defeats the true purpose of unsupervised learning and hence we envisage a paradigm of `true' self-supervision, where absolutely no annotated instances are used for training a classifier. The proposed method first pretrains a deep network through self-supervision and performs clustering on the learned features. A classifier layer is then appended to the self-supervised network and is trained by matching the distribution of the predictions to that of a predefined prior. This approach leverages the distribution of labels for supervisory signals and consequently, no image-label pair is needed. Experiments reveal that the method works on major nominal as well as ordinal classification datasets and delivers significant performance.

Related Papers

• → An Overview of Supervised Machine Learning Algorithm(2022)65 cited
• → A Supervised Machine Learning Algorithms: Applications, Challenges, and Recommendations(2023)8 cited
• → An assessment of machine learning algorithms for healthcare analysis based on improved MapReduce(2022)6 cited
• → Survey of Machine Learning Algorithms & its Applications(2021)1 cited
• Tidal Wave Prediction Using Machine Learning(2021)