mlsanityData to 7 Oct 2026

Advancing Generative Model Evaluation: A Novel Algorithm for Realistic Image Synthesis and Comparison in OCR System

arXiv 2402.17204 ↗First posted 27 Feb 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This research addresses a critical challenge in the field of generative models, particularly in the generation and evaluation of synthetic images. Given the inherent complexity of generative models and the absence of a standardized procedure for their comparison, our study introduces a pioneering algorithm to objectively assess the realism of synthetic images. This approach significantly enhances the evaluation methodology by refining the Fr'echet Inception Distance (FID) score, allowing for a more precise and subjective assessment of image quality. Our algorithm is particularly tailored to address the challenges in generating and evaluating realistic images of Arabic handwritten digits, a task that has traditionally been near-impossible due to the subjective nature of realism in image generation. By providing a systematic and objective framework, our method not only enables the comparison of different generative models but also paves the way for improvements in their design and output. This breakthrough in evaluation and comparison is crucial for advancing the field of OCR, especially for scripts that present unique complexities, and sets a new standard in the generation and assessment of high-quality synthetic images.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 88 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

29 of 88 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2014Going Deeper with Convolutionscited by 4,231
  5. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2014Conditional Generative Adversarial Netscited by 2,152
  8. 2018Sanity Checks for Saliency Mapscited by 1,149
  9. 2018AutoAugment: Learning Augmentation Policies from Datacited by 728
  10. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  11. 2016Ladder Variational Autoencoderscited by 315
  12. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
17 more
  1. 2018A Note on the Inception Scorecited by 225
  2. 2018Synthetic Data Augmentation using GAN for Improved Liver Lesion Classificationcited by 136
  3. 2020Dynamical Variational Autoencoders: A Comprehensive Reviewcited by 127
  4. 2017Improved Variational Autoencoders for Text Modeling using Dilated Convolutionscited by 81
  5. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  6. 2020The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabelingcited by 64
  7. 2022A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributescited by 56
  8. 2023Deep Learning Approaches for Data Augmentation in Medical Imaging: A Reviewcited by 48
  9. 2020Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoderscited by 30
  10. 2015A Review Paper: Noise Models in Digital Image Processingcited by 23
  11. 2017A Survey on Optical Character Recognition Systemcited by 23
  12. 2018An improvement of the convergence proof of the ADAM-Optimizercited by 19
  13. 2017Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generationcited by 18
  14. 2022Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoderscited by 17
  15. 2017Deep Learning Autoencoder Approach for Handwritten Arabic Digits Recognitioncited by 13
  16. 2016OCR Error Correction Using Character Correction and Feature-Based Word Classificationcited by 7
  17. 2019Efficient, Lexicon-Free OCR using Deep Learningcited by 5

Built on by

Not cited yet.