Towards Effective Codebookless Model for Image Classification

TL;DR

This paper introduces a codebookless image classification model that uses a single Gaussian representation, embedding it into a vector space, and employs joint learning with SVM to improve efficiency and accuracy.

Contribution

The paper proposes a novel codebookless model for image classification that simplifies representation, reduces computational cost, and incorporates background removal techniques.

Findings

Achieves competitive accuracy with state-of-the-art BoF methods

Reduces computational and storage costs through joint learning

Effectively handles background clutter with saliency-based removal

Abstract

The bag-of-features (BoF) model for image classification has been thoroughly studied over the last decade. Different from the widely used BoF methods which modeled images with a pre-trained codebook, the alternative codebook free image modeling method, which we call Codebookless Model (CLM), attracted little attention. In this paper, we present an effective CLM that represents an image with a single Gaussian for classification. By embedding Gaussian manifold into a vector space, we show that the simple incorporation of our CLM into a linear classifier achieves very competitive accuracy compared with state-of-the-art BoF methods (e.g., Fisher Vector). Since our CLM lies in a high dimensional Riemannian manifold, we further propose a joint learning method of low-rank transformation with support vector machine (SVM) classifier on the Gaussian manifold, in order to reduce computational and storage cost. To study and alleviate the side effect of background clutter on our CLM, we also present a simple yet effective partial background removal method based on saliency detection. Experiments are extensively conducted on eight widely used databases to demonstrate the effectiveness and efficiency of our CLM method.