An Interpretable Generative Model for Handwritten Digits Synthesis

An interpretable generative model for handwritten digits synthesis is proposed in this work. Modern image generative models such as the variational autoencoder (VAE) are trained by backpropagation (BP). The training process is complex, and its underlying mechanism is not transparent. Here, we presen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings - International Conference on Image Processing s. 1910 - 1914
Hlavní autoři: Zhu, Yao, Suri, Saksham, Kulkarni, Pranav, Chen, Yueru, Duan, Jiali, Kuo, C.-C. Jay
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2019
Témata:
Decoding
explainable machine learning
feedforward Design
Generative model
Image reconstruction
Image synthesis
Kernel
Principal component analysis
principal component analysis (PCA)
Training
Transforms
variational autoencoder (VAE)
ISSN:2381-8549
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:An interpretable generative model for handwritten digits synthesis is proposed in this work. Modern image generative models such as the variational autoencoder (VAE) are trained by backpropagation (BP). The training process is complex, and its underlying mechanism is not transparent. Here, we present an explainable generative model using a feedforward design methodology without BP. Being similar to VAEs, it has an encoder and a decoder. For the encoder design, we derive principal-component-analysis-based (PCA-based) transform kernels using the covariance of its inputs. This process converts input images of correlated pixels to uncorrelated spectral components, which play the same role as latent variables in a VAE system. For the decoder design, we convert randomly generated spectral components to synthesized images through the inverse PCA transform. A subject test is conducted to compare the quality of digits generated using the proposed method and the VAE method. They offer comparable perceptual quality yet our model can be obtained at much lower complexity.
ISSN:2381-8549
DOI:10.1109/ICIP.2019.8803129