IIARD International Institute of Academic Research and Development

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY (IJCSMT )

E-ISSN 2545-5699
P-ISSN 2695-1924
VOL. 10 NO. 3 2024
DOI: 10.56201/ijcsmt.v10.no3.2024.pg67.81

---

Leveraging EfficientNet and Amortized Stochastic Variational Inference for Improved Transfer Learning in VAEs in Mobile and Resource-Constrained Environments

Ene, D. S., Anireh, V. I. E., Matthias, D., Bennett, E. O.

---

Abstract

Variational Autoencoders (VAEs) have become a cornerstone in generative modeling, providing a powerful framework for learning latent representations of data. Recent advances in neural architectures, such as EfficientNet, offer promising avenues for improving VAE performance while reducing resource consumption. This paper aims to explore the integration of these advancements to enhance transfer learning in VAEs for mobile and resource- constrained environments. The proposed model integrates the Adam optimizer with Amortized Stochastic Variationsal Inference (ASVI), adaptive hyperparameter tuning, and specific miniaturization techniques. The ELBO is optimised to maximise the predicted log-likelihood while minimising the KL divergence between the variational posterior and the prior over latent variables. We evaluate our proposed model on three benchmark datasets: MNIST, CIFAR-10, and CelebA. Our experimental results demonstrate significant performance gains in terms of reconstruction quality, classification accuracy, and computational efficiency. Our proposed model sets a new benchmark for transfer learning, paving the way for further research in this direction.

keywords:

VAE, ASVI, EnhancedNet, Autoencoders, Variational Inference, CNN, Neural

---

References:

[1].
Kingma, D. P., & Welling, M. (2013). Auto-Encoding Variational Bayes. arXiv
preprint arXiv:1312.6114.

[2].
Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking Model Scaling for
Convolutional Neural Networks. arXiv preprint arXiv:1905.11946.

[3].
Gershman, S., Hoffman, M. D., & Blei, D. M. (2014). Amortized Inference in
Probabilistic Reasoning. arXiv preprint arXiv:1411.2581.

[4].
Kim, M. (2022). Gaussian process modeling of approximate inference errors for
variational autoencoders. In Proceedings of the IEEE/CVF Conference on
Computer Vision and Pattern Recognition (pp. 244-253).

[5].
Rezende, D. J., Mohamed, S., & Wierstra, D. (2014). Stochastic
Backpropagation and Approximate Inference in Deep Generative Models. arXiv
preprint arXiv:1401.4082.

[6].
Salimans, T., Kingma, D. P., & Welling, M. (2015). Markov Chain Monte Carlo
and Variational Inference: Bridging the Gap. arXiv preprint arXiv:1410.6460.

DOWNLOAD PDF

---

Back