NepScript Genesis：用于手写天城文数字合成的神经架构搜索
NepScript Genesis: Neural Architecture Search for Handwritten Devanagari Digit Synthesis
浏览论文内容
中文总结 AI 辅助
该研究提出NepScript Genesis框架，用NAS优化GAN合成手写天城文数字，自适应探索策略效果最优，生成的数字可提升低资源场景下的CNN分类准确率。
中文摘要 AI 辅助
本文介绍了NepScript Genesis，这是一个用于自动生成对抗网络（GAN）发现的神经架构搜索（NAS）框架，应用于条件手写天城文数字合成。我们将五种NAS策略与精心构建的深度卷积GAN（DCGAN）基准进行比较，基准的FID为332.28。架构选择采用由新型领域感知评估指标（增强分数）引导的两阶段流程。结果表明，自适应探索实现了最优的质量-效率权衡，达到79.12的FID（较基准提升76.19%），且在不到1个GPU小时内，在NAS策略中具有最高的模式覆盖率（召回率=0.531）。此外，我们证明在搜索阶段融入特定脚本的结构启发式方法可防止早期模式崩溃。在下游低资源评估中，用最佳NAS模型生成的GAN数字扩充每类250个真实训练样本，使CNN分类准确率从91.0%提升至96.5%（+5.5个百分点），表明NAS优化的合成数字质量足够，可在真实数据稀缺时为实际识别流程带来益处。
英文摘要
This paper introduces NepScript Genesis, a Neural Architecture Search (NAS) framework for automated Generative Adversarial Network (GAN) discovery, applied to conditional Devanagari handwritten digit synthesis. We compare five NAS strategies against a carefully constructed Deep Convolutional GAN (DCGAN) baseline (FID=332.28). Architecture selection utilizes a two-stage pipeline guided by a novel domain-aware evaluation metric (Enhanced Score). Results demonstrate that Adaptive Exploration achieves the optimal quality-efficiency trade-off, attaining an FID of 79.12 -- a 76.19% improvement over the baseline -- and the highest mode coverage among the NAS strategies (Recall=0.531) in under one GPU-hour. Furthermore, we demonstrate that incorporating script-specific structural heuristics into the search phase prevents early-stage mode collapse. In a downstream low-resource evaluation, augmenting 250 real training samples per class with GAN-generated digits from the best NAS model improves CNN classification accuracy from 91.0% to 96.5% (+5.5 percentage points), demonstrating that NAS-optimized synthesis produces digits of sufficient quality to benefit practical recognition pipelines when real data is scarce.
