Zero-shot Generation of Training Data with Denoising Diffusion Probabilistic Model for Handwritten Chinese Character Recognition.
Dongnan GuiKai ChenHaisong DingQiang HuoPublished in: CoRR (2023)
Keyphrases
- denoising
- handwritten chinese character recognition
- probabilistic model
- training data
- nonlinear diffusion
- diffusion processes
- image denoising
- total variation
- noisy images
- natural images
- image processing
- bayesian networks
- generative model
- test data
- language model
- data sets
- training set
- learning algorithm
- denoising algorithm
- test set
- prior knowledge
- decision trees
- diffusion process
- wavelet domain
- generalization error
- training instances
- generation process
- noise removal
- gaussian noise
- training examples
- training process
- anisotropic diffusion
- wavelet packet
- object categories
- training samples
- denoising methods
- diffusion model
- object detection
- domain knowledge
- diffusion equation
- support vector machine
- text classification
- information retrieval
- learned from training data
- neural network