Deep Boosting: Layered Feature Mining for General Image Classification
This addresses the problem of limited performance in general image classification due to reliance on handcrafted features, offering a novel computational approach.
The paper tackles the challenge of constructing effective image representations by proposing a layered feature mining architecture that assembles primitive filters into compositional features using boosting, achieving superior performance over state-of-the-art methods on public datasets.
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.