Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning

TL;DR

This paper introduces a two-stage framework combining contrastive learning and teacher-student distillation to learn script similarity, enabling effective recognition and clustering of diverse writing systems without explicit evolutionary labels.

Contribution

It presents a novel two-stage method that leverages supervised contrastive learning and unsupervised distillation to discover script similarities and improve glyph recognition.

Findings

Effective few-shot glyph recognition achieved

Meaningful script clustering demonstrated

Bridges supervised and unsupervised learning for script analysis

Abstract

Learning similarity metrics for glyphs and writing systems faces a fundamental challenge: while individual graphemes within invented alphabets can be reliably labeled, the historical relationships between different scripts remain uncertain and contested. We propose a two-stage framework that addresses this epistemological constraint. First, we train an encoder with contrastive loss on labeled invented alphabets, establishing a teacher model with robust discriminative features. Second, we extend to historically attested scripts through teacher-student distillation, where the student learns unsupervised representations guided by the teacher's knowledge but free to discover latent cross-script similarities. The asymmetric setup enables the student to learn deformation-invariant embeddings while inheriting discriminative structure from clean examples. Our approach bridges supervised contrastive learning and unsupervised discovery, enabling both hard boundaries between distinct systems and soft similarities reflecting potential historical influences. Experiments on diverse writing systems demonstrate effective few-shot glyph recognition and meaningful script clustering without requiring ground-truth evolutionary relationships.