Metraipolis › archive › dc_6b1b3b7033db
NepScript Genesis: Neural Architecture Search for Handwritten Devanagari Digit Synthesis — arXiv:2608.29540
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29540
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T09:59:00.830Z
- SHA-256 of the archived text
da1589020e8fdd365d9169293bc7cf185f2a6c2a80787b338f0dc0a821e549d9- Stable URL of this page
https://metraipolis.com/documento/dc_6b1b3b7033db
How to cite
NepScript Genesis: Neural Architecture Search for Handwritten Devanagari Digit Synthesis — arXiv:2608.29540 — arXiv (en), https://arxiv.org/abs/2608.29540 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b1b3b7033db (Metraipolis archive dc_6b1b3b7033db, sha256 da1589020e8fdd365d9169293bc7cf185f2a6c2a80787b338f0dc0a821e549d9)
BibTeX
@misc{dc6b1b3b7033db,
title = {NepScript Genesis: Neural Architecture Search for Handwritten Devanagari Digit Synthesis — arXiv:2608.29540},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29540},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b1b3b7033db; sha256 da1589020e8fdd365d9169293bc7cf185f2a6c2a80787b338f0dc0a821e549d9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29540. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.29540 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T09:28:48.045Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).