홈 › Papers

A Seed-Augment-Train Framework for Universal Digit Classification

2019-03-27 · ICLR Workshop DeepGenStruct 2019 · Vinay Uday Prabhu, Sanghyun Han, Dian Ang Yap, Mihail Douhaniaris, Preethi Seshadri

In this paper, we propose a Seed-Augment-Train/Transfer (SAT) framework that contains a synthetic seed image dataset generation procedure for languages with different numeral systems using freely available open font file datasets. This seed dataset of images is then augmented to create a purely synthetic training dataset, which is in turn used to train a deep neural network and test on held-out real world handwritten digits dataset spanning five Indic scripts, Kannada, Tamil, Gujarati, Malayalam, and Devanagari. We showcase the efficacy of this approach both qualitatively, by training a Boundary-seeking GAN (BGAN) that generates realistic digit images in the five languages, and also qualitatively by testing a CNN trained on the synthetic data on the real-world datasets. This establishes not only an interesting nexus between the font-datasets-world and transfer learning but also provides a recipe for universal-digit classification in any script.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDataset GenerationTransfer Learning

Fonts-2-Handwriting: A Seed-Augment-Train framework for universal digit classification

2019-05-16 · Vinay Uday Prabhu, Sanghyun Han, Dian Ang Yap, Mihail Douhaniaris 외

Dataset Generation General Classification Transfer Learning

Cross-seed explainability using Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoders

2026-07-09 · Bendegúz Váradi, Zoltán Kmetty arxiv

We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed feature universality is a fundamental ch…

One Model for All: Universal Pre-training for EEG based Emotion Recognition across Heterogeneous Datasets and Paradigms

2025-11-11 · Xiang Li, You Li, Yazhou Zhang arxiv

EEG-based emotion recognition is hampered by profound dataset heterogeneity (channel/subject variability), hindering generalizable models. Existing approaches struggle to transfer knowledge effectively. We propose 'One M…

Contrastive Learning Emotion Recognition

PN-QNN: Harnessing Physical Noise as a Native Regularizer in Photonic Hybrid Quantum Neural Networks

2026-07-22 · Farah Elnakhal, Alberto Marchisio, Nouhaila Innan, Gabriel Falcao 외 arxiv

Physical noise in near-term quantum hardware is usually treated as a nuisance to suppress. We ask whether it can instead act as a hardware-native regularizer for photonic hybrid quantum-classical neural networks (PHQCNNs…

Polymorphism Is Rotation: Operational Mechanistic Interpretability from a Two-Layer Transformer to Pythia-70m

2026-05-23 · Jordan F. McCann arxiv

Independently trained transformers compute the same function in residual-stream bases that differ by a uniform random rotation on $\mathrm{SO}(d_{\mathrm{model}})$. We call this phenomenon polymorphism: same function, mu…