Revisiting deep fisher vectors: using fisher information to improve object classification

Ahmed, Sarah, Azim, Tayyaba, Early, Joseph Arthur and Ramchurn, Sarvapali (2022) Revisiting deep fisher vectors: using fisher information to improve object classification. British Machine Vision Conference, , London, United Kingdom. 21 - 24 Nov 2022. 10 pp .

Abstract

Although deep learning models have become the gold standard in achieving outstanding results on a large variety of computer vision and machine learning tasks, the use of kernel methods has still not gone out of trend because of its potential to beat deep learning performances at a number of occasions. Given the potential of kernel techniques, prior works have also proposed the use of hybrid approaches combining deep learning with kernel learning to complement their respective strengths and weaknesses. This work develops this idea further by introducing an improved version of Fisher kernels derived from the deep Boltzmann machines (DBM). Our improved deep Fisher kernel (IDFK) utilises an approximation of the Fisher information matrix to derive improved Fisher vectors. We show IDFK can be utilised to retain a high degree of class separability, making it appropriate for classification and retrieval tasks. The efficacy of the proposed approach is evaluated on three benchmark data sets: MNIST, USPS and Alphanumeric, showing an improvement in classification performance over existing kernel approaches, and comparable performance to deep learning methods, but with much reduced computational costs. Using explainable AI methods, we also demonstrate why our IDFK leads to better classification performance.

This record has no associated files available for download.

Contributors

Author: Joseph Arthur Early

Author: Sarvapali Ramchurn

Download statistics