Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes

Abstract

We consider the problem of semi-supervised bootstrap learning for scene categorization (e.g classifying images into categories such as coast and desert). Existing semi-supervised approaches are typically unreliable and face semantic drift because the learning task is under-constrained. This is primarily because they ignore the strong interactions that often exist between scene categories, such as the common attributes shared across categories, as well as the attributes which make one scene different from another. The goal of this paper is to exploit these relationships and constrain the semi-supervised learning problem. For example, the knowledge of an image instance being an auditorium can improve labelling of amphitheaters by enforcing constraints that an amphitheater image should have more circular structures than an auditorium image. We propose constraints based on mutual exclusion, binary attributes and comparative attributes and show that they help us to constrain the learning problem and avoid semantic drift. We demonstrate the effectiveness of our approach through extensive experiments including results on a very large dataset of one million images.