Deep Boosting: Joint Feature Selection and Analysis Dictionary Learning in Hierarchy
This work addresses the challenge of building deep architectures for image classification, offering a novel method that could benefit computer vision researchers, though it appears incremental in combining existing techniques like boosting and dictionary learning.
The authors tackled the problem of extending traditional image classification pipelines into deep architectures by proposing a deep boosting framework that jointly performs feature selection and dictionary learning layer-by-layer. Their approach outperformed existing state-of-the-art methods in several visual recognition tasks.
This work investigates how the traditional image classification pipelines can be extended into a deep architecture, inspired by recent successes of deep neural networks. We propose a deep boosting framework based on layer-by-layer joint feature boosting and dictionary learning. In each layer, we construct a dictionary of filters by combining the filters from the lower layer, and iteratively optimize the image representation with a joint discriminative-generative formulation, i.e. minimization of empirical classification error plus regularization of analysis image generation over training images. For optimization, we perform two iterating steps: i) to minimize the classification error, select the most discriminative features using the gentle adaboost algorithm; ii) according to the feature selection, update the filters to minimize the regularization on analysis image representation using the gradient descent method. Once the optimization is converged, we learn the higher layer representation in the same way. Our model delivers several distinct advantages. First, our layer-wise optimization provides the potential to build very deep architectures. Second, the generated image representation is compact and meaningful. In several visual recognition tasks, our framework outperforms existing state-of-the-art approaches.