AMR-CCR: Anchored Modular Retrieval for Continual Chinese Character Recognition
This work is significant for cultural heritage digitization by enabling scalable and adaptable recognition of ancient Chinese characters as new materials and scripts are discovered, addressing the challenges of continual class growth and intra-class diversity.
This paper addresses the challenge of Continual Chinese Character Recognition (Continual CCR) in non-stationary real-world workflows, where new character classes and scripts are continuously added. They propose AMR-CCR, an anchored modular retrieval framework that uses embedding-based dictionary matching in a shared multimodal space, allowing new classes to be added by simply extending the dictionary.
Ancient Chinese character recognition is a core capability for cultural heritage digitization, yet real-world workflows are inherently non-stationary: newly excavated materials are continuously onboarded, bringing new classes in different scripts, and expanding the class space over time. We formalize this process as Continual Chinese Character Recognition (Continual CCR), a script-staged, class-incremental setting that couples two challenges: (i) scalable learning under continual class growth with subtle inter-class differences and scarce incremental data, and (ii) pronounced intra-class diversity caused by writing-style variations across writers and carrier conditions. To overcome the limitations of conventional closed-set classification, we propose AMR-CCR, an anchored modular retrieval framework that performs recognition via embedding-based dictionary matching in a shared multimodal space, allowing new classes to be added by simply extending the dictionary. AMR-CCR further introduces a lightweight script-conditioned injection module (SIA+SAR) to calibrate newly onboarded scripts while preserving cross-stage embedding compatibility, and an image-derived multi-prototype dictionary that clusters within-class embeddings to better cover diverse style modes. To support systematic evaluation, we build EvoCON, a six-stage benchmark for continual script onboarding, covering six scripts (OBC, BI, SS, SAC, WSC, CS), augmented with meaning/shape descriptions and an explicit zero-shot split for unseen characters without image exemplars.