Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification

TL;DR

This paper introduces SWIS, a decorrelation-based self-supervised learning framework tailored for writer identification, demonstrating superior performance over existing methods and pioneering its application in writer verification tasks.

Contribution

The paper proposes SWIS, a novel decorrelation-based self-supervised framework for writer identification, standardizing features to improve disentangled stroke representation learning.

Findings

Outperforms contemporary self-supervised frameworks on writer identification benchmarks.

Surpasses several supervised methods in writer verification accuracy.

First application of self-supervised learning for writer verification tasks.

Abstract

Self-supervised learning has developed rapidly over the last decade and has been applied in many areas of computer vision. Decorrelation-based self-supervised pretraining has shown great promise among non-contrastive algorithms, yielding performance at par with supervised and contrastive self-supervised baselines. In this work, we explore the decorrelation-based paradigm of self-supervised learning and apply the same to learning disentangled stroke features for writer identification. Here we propose a modified formulation of the decorrelation-based framework named SWIS which was proposed for signature verification by standardizing the features along each dimension on top of the existing framework. We show that the proposed framework outperforms the contemporary self-supervised learning framework on the writer identification benchmark and also outperforms several supervised methods as well. To the best of our knowledge, this work is the first of its kind to apply self-supervised learning for learning representations for writer verification tasks.