Abstract
There have been many compression standards developed during the past few decades and technological advances has resulted in introducing many methodologies with promising results. As far as PSNR metric is concerned, there is a performance gap between reigning compression standards and learned compression algorithms. Based on research, we experimented using an accurate entropy model on the learned compression algorithms to determine the rate-distortion performance. In this paper, discretized Gaussian Mixture likelihood is proposed to determine the latent code parameters in order to attain a more flexible and accurate model of entropy. Moreover, we have also enhanced the performance of the work by introducing recent attention modules in the network architecture. Simulation results indicate that when compared with the previously existing techniques using high-resolution and Kodak datasets, the proposed work achieves a higher rate of performance. When MS-SSIM is used for optimization, our work generates a more visually pleasant image.
References
- O’Hagan, A., Murphy, T. B., Scrucca, L., & Gormley, I. C. (2019). Investigation of parameter uncertainty in clustering using a Gaussian mixture model via jackknife, bootstrap and weighted likelihood bootstrap. Computational Statistics, 34(4), 1779-1813.
- Ai, J., Luo, Q., Yang, X., Yin, Z., & Xu, H. (2019). Outliers-robust CFAR detector of Gaussian clutter based on the truncated-maximum-likelihood-estimator in SAR imagery. IEEE Transactions on Intelligent Transportation Systems, 21(5), 2039-2049.
- Coons, J. I., Marigliano, O., & Ruddy, M. (2020). Maximum likelihood degree of the two-dimensional linear Gaussian covariance model. Algebraic Statistics, 11(2), 107-123.
- Weber, J. H., & Immink, K. A. S. (2018). Maximum likelihood decoding for Gaussian noise channels with gain or offset mismatch. IEEE Communications Letters, 22(6), 1128-1131.
- Kharrati-Kopaei, M. (2021). On the exact distribution of the likelihood ratio test statistic for testing the homogeneity of the scale parameters of several inverse Gaussian distributions. Computational Statistics, 1-16.
- D.,Ruth Anita Shirley, A., Ranjani, K., Arunachalam, G., & Janeera, D. A. (2021). Automatic Distributed Gardening System Using Object Recognition and Visual Servoing. In Inventive Communication and Computational Technologies (pp. 359-369). Springer, Singapore.
- Sellentin, E., & Heavens, A. F. (2018). On the insufficiency of arbitrarily precise covariance matrices: non-Gaussian weak-lensing likelihoods. Monthly Notices of the Royal Astronomical Society, 473(2), 2355-2363.
- Ippoliti, L., Martin, R. J., & Romagnoli, L. (2018). Efficient likelihood computations for some multivariate Gaussian Markov random fields. Journal of Multivariate Analysis, 168, 185-200.
- Rios, G., & Tobar, F. (2018, July). Learning non-Gaussian time series using the Box-Cox Gaussian process. In 2018 International Joint Conference on Neural Networks (IJCNN) (pp. 1-8). IEEE.
- Subba Rao, S., & Yang, J. (2020). Reconciling the Gaussian and Whittle Likelihood with an application to estimation in the frequency domain. arXiv e-prints, arXiv-2001.
- Xie, X., Zhang, Y., Wang, X., & Peng, D. (2019). A Mixture Likelihood Model of the Anisotropic Gaussian and Uniform Distributions for Accurate Oblique Image Point Matching. IEEE Geoscience and Remote Sensing Letters, 16(9), 1437-1441.
- Manoharan, S. (2020). Population Based Meta Heuristics Algorithm for Performance Improvement of Feed Forward Neural Network. Journal of Soft Computing Paradigm (JSCP), 2(01), 36-46.
- Dhaya, R. (2020). Improved Image Processing Techniques for User Immersion Problem Alleviation in Virtual Reality Environments. Journal of Innovative Image Processing (JIIP), 2(02), 77-84.