Efficient Image Categorization with Sparse Fisher Vector

TL;DR

This paper introduces Sparse Fisher Vector (SFV), a simplified and faster image representation method that maintains high categorization accuracy, by accelerating Fisher coding through locality strategies and theoretical analysis.

Contribution

The paper proposes SFV, a novel sparse coding method that significantly speeds up Fisher vector computation while preserving recognition performance.

Findings

SFV achieves several-fold speedup over traditional FV.

SFV maintains comparable image categorization accuracy.

Theoretical analysis explains the relationship between coding and pooling steps.

Abstract

In object recognition, Fisher vector (FV) representation is one of the state-of-art image representations ways at the expense of dense, high dimensional features and increased computation time. A simplification of FV is attractive, so we propose Sparse Fisher vector (SFV). By incorporating locality strategy, we can accelerate the Fisher coding step in image categorization which is implemented from a collective of local descriptors. Combining with pooling step, we explore the relationship between coding step and pooling step to give a theoretical explanation about SFV. Experiments on benchmark datasets have shown that SFV leads to a speedup of several-fold of magnitude compares with FV, while maintaining the categorization performance. In addition, we demonstrate how SFV preserves the consistence in representation of similar local features.