Learning a Hierarchical Compositional Shape Vocabulary for Multi-class Object Representation

TL;DR

This paper introduces a new hierarchical framework for learning shape vocabularies that efficiently represent multiple object classes, enabling fast inference and scalable recognition performance.

Contribution

It proposes a novel method for learning hierarchical compositional shape vocabularies that automatically discover spatial configurations without hand-crafted features.

Findings

Achieves state-of-the-art detection performance

Scales favorably with the number of object classes

Enables faster inference and shorter training times

Abstract

Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a higher number of object classes. However, the success of the hierarchical approaches so far has been hindered by the use of hand-crafted features or predetermined grouping rules. This paper presents a novel framework for learning a hierarchical compositional shape vocabulary for representing multiple object classes. The approach takes simple contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class-specific shape compositions, each exerting a high degree of shape variability. At the top-level of the vocabulary, the compositions are sufficiently large and complex to represent the whole shapes of the objects. We learn the vocabulary layer after layer, by gradually increasing the size of the window of analysis and reducing the spatial resolution at which the shape configurations are learned. The lower layers are learned jointly on images of all classes, whereas the higher layers of the vocabulary are learned incrementally, by presenting the algorithm with one object class after another. The experimental results show that the learned multi-class object representation scales favorably with the number of object classes and achieves a state-of-the-art detection performance at both, faster inference as well as shorter training times.