Deep Boosting: Layered Feature Mining for General Image Classification

TL;DR

This paper introduces a layered feature mining architecture that combines primitive filters and boosting to create expressive, discriminative image representations for general image classification, outperforming existing methods.

Contribution

It proposes a novel layered framework that assembles primitive filters into compositional features using boosting, enhancing image representation and classification performance.

Findings

Superior performance on public datasets

Effective layered feature construction

Outperforms state-of-the-art methods

Abstract

Constructing effective representations is a critical but challenging problem in multimedia understanding. The traditional handcraft features often rely on domain knowledge, limiting the performances of exiting methods. This paper discusses a novel computational architecture for general image feature mining, which assembles the primitive filters (i.e. Gabor wavelets) into compositional features in a layer-wise manner. In each layer, we produce a number of base classifiers (i.e. regression stumps) associated with the generated features, and discover informative compositions by using the boosting algorithm. The output compositional features of each layer are treated as the base components to build up the next layer. Our framework is able to generate expressive image representations while inducing very discriminate functions for image classification. The experiments are conducted on several public datasets, and we demonstrate superior performances over state-of-the-art approaches.