Reconciliation of Statistical and Spatial Sparsity For Robust Image and Image-Set Classification

TL;DR

This paper introduces J3S, a novel joint statistical and spatial sparse representation method that models local patch structures and global distributions for robust image and image-set classification, especially in noisy or limited data scenarios.

Contribution

The paper proposes the first method to jointly utilize global statistics and local patch structures via sparse representation for image classification.

Findings

J3S outperforms state-of-the-art methods on multiple datasets.

The approach effectively handles noisy and limited data scenarios.

Experimental results demonstrate improved robustness and accuracy.

Abstract

Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches. However, there are still various challenges of image classifications in practice, such as classifying noisy image or image-set queries and training deep image classification models over the limited-scale dataset. Instead of applying generic deep features, the model-based approaches can be more effective and data-efficient for robust image and image-set classification tasks, as various image priors are exploited for modeling the inter- and intra-set data variations while preventing over-fitting. In this work, we propose a novel Joint Statistical and Spatial Sparse representation, dubbed \textit{J3S}, to model the image or image-set data for classification, by reconciling both their local patch structures and global Gaussian distribution mapped into Riemannian manifold. To the best of our knowledge, no work to date utilized both global statistics and local patch structures jointly via joint sparse representation. We propose to solve the joint sparse coding problem based on the J3S model, by coupling the local and global image representations using joint sparsity. The learned J3S models are used for robust image and image-set classification. Experiments show that the proposed J3S-based image classification scheme outperforms the popular or state-of-the-art competing methods over FMD, UIUC, ETH-80 and YTC databases.