Bridging Data Trials and Task Barriers: A Unified Framework for Sketch Biometric Identification

2026-05-17

AI Summary

This work addresses key challenges in cross-modal and cross-task sketch-based biometric recognition—namely, the scarcity of real-world data, high annotation costs, privacy concerns, and limited model generalization—by proposing the first unified framework. The approach leverages an efficient synthetic sketch generation pipeline to construct large-scale training data and incorporates a task-sequential continual learning mechanism: it first pretrains on generic portrait sketches and then incrementally learns face sketch tasks, supported by a trusted sample replay strategy to preserve performance across tasks. The study introduces SketchUnified-BioID, the first large-scale benchmark dataset for this domain, and demonstrates the framework’s effectiveness and superiority across diverse sketch recognition tasks.

Abstract

Different from existing cross-modality identification tasks (e.g., heterogeneous face recognition, sketch re-identification, etc.), we introduce a novel yet practical setting for these related identification tasks, named \textbf{sketch biometric identification}, which aims to continually train a unified model across different data domains, even diverse identification tasks. Sketch biometric identification faces challenges, including scarce real sketch data, high annotation costs, privacy risks, and insufficient generalization ability of cross-task models. Existing methods usually rely on limited real data or single-task optimization, making it difficult to effectively address the joint challenges of cross-modality and cross-task. This paper proposes a unified framework that integrates efficient synthetic sketch generation and task-sequential continual learning. First, we design an efficient pipeline to generate a large-scale and high-quality synthetic person and face sketch data, which significantly reduces costs and avoids privacy risks. Meanwhile, we enhance the model's robustness by fusing real data. Second, we construct a universal unified framework for sketch biometric identification, which adopts a task-sequential training strategy: the model first completes sketch person re-identification learning on the person dataset; subsequently, it maintains the acquired person recognition capability through a trusted sample replay technique and seamlessly performs incremental training on the face dataset. This enables a single model to simultaneously handle the cross-task capabilities of multiple sketch biometric identification tasks. To support the study of the mentioned sketch biometric identification, we built a new large-scale benchmark, SketchUnified-BioID, with several practical evaluation protocols.

Problem

• sketch biometric identification
• cross-modality
• cross-task
• data scarcity
• generalization

Innovation

• sketch biometric identification
• synthetic sketch generation
• task-sequential continual learning
• cross-modality learning
• unified framework