Confidence-Guided Diffusion Augmentation for Enhanced Bangla Compound Character Recognition

• URL: http://arxiv.org/abs/2605.10916v2
• Date: Tue, 12 May 2026 16:00:08 GMT
• Title: Confidence-Guided Diffusion Augmentation for Enhanced Bangla Compound Character Recognition
• Abstract summary: Existing Bangla handwritten character recognition systems struggle to generalize across diverse writing styles.<n>We propose a confidence-guided diffusion augmentation framework for low-resolution Bangla compound character recognition.<n>Our best-performing model achieves 89.2% classification accuracy, surpassing the previously published AIBangla benchmark.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recognition of handwritten Bangla compound characters remains a challenging problem due to complex character structures, large intra-class variation, and limited availability of high-quality annotated data. Existing Bangla handwritten character recognition systems often struggle to generalize across diverse writing styles, particularly for compound characters containing intricate ligatures and diacritical variations. In this work, we propose a confidence-guided diffusion augmentation framework for low-resolution Bangla compound character recognition. Our framework combines class-conditional diffusion modeling with classifier guidance to synthesize high-quality handwritten compound character samples. To further improve generation quality, we introduce Squeeze-and-Excitation enhanced residual blocks within the diffusion model's U-Net backbone. We additionally propose a confidence-based filtering mechanism where pre-trained classifiers act as quality gates to retain only highly class-consistent synthetic samples. The filtered synthetic images are fused with the original training data and used to retrain multiple classification architectures. Experiments conducted on the AIBangla compound character dataset demonstrate consistent performance improvements across ResNet50, DenseNet121, VGG16, and Vision Transformer architectures. Our best-performing model achieves 89.2\% classification accuracy, surpassing the previously published AIBangla benchmark by a substantial margin. The results demonstrate that quality-aware diffusion augmentation can effectively enhance handwritten character recognition performance in low-resource script domains.

Related papers

• SpiS-GAN: Spiral-Modulated Handwriting Synthesis with Star Operation [4.223500604789643]
  Training robust handwriting recognition (HTR) systems requires massive amounts of annotated data.<n>Previous approaches fail to effectively trace cursive handwriting due to fixed-grid receptive field.<n>Existing approaches lack explicit edge constraints, often resulting in blurred stroke boundaries.<n>This study proposes a Spiral-Modulated Handwriting Synthesis framework based on Generative Adrial Networks (SpiS-GAN)
  arXiv  Detail & Related papers  (2026-07-08T03:21:19Z)
• Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition [55.189113121465816]
  We propose a novel correlation adaptation prompt network (CAPNET) for long-tailed multi-label visual recognition.<n>CAPNET explicitly models correlations from CLIP's textual encoder.<n>It improves generalization through test-time ensembling and realigns visual-textual modalities.
  arXiv  Detail & Related papers  (2025-11-25T18:57:28Z)
• FW-GAN: Frequency-Driven Handwriting Synthesis with Wave-Modulated MLP Generator [4.94997283141601]
  We propose FW-GAN, a one-shot handwriting synthesis framework that generates realistic, writer-consistent text from a single example.<n>Our generator integrates a phase-aware Wave-MLP to better capture spatial relationships while preserving subtle stylistic cues.<n> Experiments on Vietnamese and English handwriting datasets demonstrate that FW-GAN generates high-quality, style-consistent handwriting.
  arXiv  Detail & Related papers  (2025-08-28T17:44:52Z)
• Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognition [7.913119666154837]
  Handwritten text recognition aims to convert visual input into machine-readable text.<n>Character sets change over time, and character frequency distributions shift across historical periods or regions.<n>We propose a novel loss function that incorporates the Wasserstein distance between the character frequency distribution of the predicted text and a target distribution.
  arXiv  Detail & Related papers  (2025-06-11T15:20:30Z)
• Your Image Generator Is Your New Private Dataset [4.09225917049674]
  Generative diffusion models have emerged as powerful tools to synthetically produce training data.<n>This paper proposes the Text-Conditioned Knowledge Recycling pipeline to tackle these challenges.<n>The pipeline is rigorously evaluated on ten diverse image classification benchmarks.
  arXiv  Detail & Related papers  (2025-04-06T18:46:08Z)
• Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing [71.29488677105127]
  Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. We propose a contrastive learning-based STR framework by leveraging synthetic and real unlabeled data without any human cost. Our method achieves SOTA performance (94.7% and 70.9% average accuracy on common benchmarks and Union14M-Benchmark.
  arXiv  Detail & Related papers  (2024-11-23T15:24:47Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• ENTED: Enhanced Neural Texture Extraction and Distribution for Reference-based Blind Face Restoration [51.205673783866146]
  We present ENTED, a new framework for blind face restoration that aims to restore high-quality and realistic portrait images. We utilize a texture extraction and distribution framework to transfer high-quality texture features between the degraded input and reference image. The StyleGAN-like architecture in our framework requires high-quality latent codes to generate realistic images.
  arXiv  Detail & Related papers  (2024-01-13T04:54:59Z)
• Diversified in-domain synthesis with efficient fine-tuning for few-shot classification [64.86872227580866]
  Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. We propose DISEF, a novel approach which addresses the generalization challenge in few-shot learning using synthetic data. We validate our method in ten different benchmarks, consistently outperforming baselines and establishing a new state-of-the-art for few-shot classification.
  arXiv  Detail & Related papers  (2023-12-05T17:18:09Z)
• Offline Detection of Misspelled Handwritten Words by Convolving Recognition Model Features with Text Labels [0.0]
  We introduce the task of comparing a handwriting image to text. Our model's classification head is trained entirely on synthetic data created using a state-of-the-art generative adversarial network. Such massive performance gains can lead to significant productivity increases in applications utilizing human-in-the-loop automation.
  arXiv  Detail & Related papers  (2023-09-18T21:13:42Z)
• Self-Adversarial Learning with Comparative Discrimination for Text Generation [111.18614166615968]
  We propose a novel self-adversarial learning (SAL) paradigm for improving GANs' performance in text generation. During training, SAL rewards the generator when its currently generated sentence is found to be better than its previously generated samples. Experiments on text generation benchmark datasets show that our proposed approach substantially improves both the quality and the diversity.
  arXiv  Detail & Related papers  (2020-01-31T07:50:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.