Saved in:
Bibliographic Details
Main Authors: Roman, Claire, Meyer, Philippe
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.06180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911493119803392
author Roman, Claire
Meyer, Philippe
author_facet Roman, Claire
Meyer, Philippe
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_06180
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning
Roman, Claire
Meyer, Philippe
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
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.
title Contrastive-to-Self-Supervised: A Two-Stage Framework for Script Similarity Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Machine Learning
url https://arxiv.org/abs/2603.06180