Labeling the Features Not the Samples: Efficient Video Classification with Minimal Supervision

TL;DR

This paper introduces a nearly unsupervised method for feature selection and video classification that requires minimal labeled data, achieving high accuracy and efficiency in large-scale recognition tasks.

Contribution

It presents a novel feature sign-based approach enabling effective feature selection and classification with minimal supervision and low computational cost.

Findings

Outperforms established feature selection methods in speed and accuracy

Requires only one labeled sample per class for feature sign estimation

Effective in scenarios with very limited training data

Abstract

Feature selection is essential for effective visual recognition. We propose an efficient joint classifier learning and feature selection method that discovers sparse, compact representations of input features from a vast sea of candidates, with an almost unsupervised formulation. Our method requires only the following knowledge, which we call the \emph{feature sign}---whether or not a particular feature has on average stronger values over positive samples than over negatives. We show how this can be estimated using as few as a single labeled training sample per class. Then, using these feature signs, we extend an initial supervised learning problem into an (almost) unsupervised clustering formulation that can incorporate new data without requiring ground truth labels. Our method works both as a feature selection mechanism and as a fully competitive classifier. It has important properties, low computational cost and excellent accuracy, especially in difficult cases of very limited training data. We experiment on large-scale recognition in video and show superior speed and performance to established feature selection approaches such as AdaBoost, Lasso, greedy forward-backward selection, and powerful classifiers such as SVM.