While the beta-VAE family is aiming to find disentangled representations and acquire human-interpretable generative factors, like what an ICA (from the linear domain) does, we propose Full Encoder, a novel unified autoencoder framework as a correspondence to PCA in the non-linear domain. The idea is to train an autoencoder with one latent variable first, then involve more latent variables progressively to refine the reconstruction results. The Full Encoder is also a latent variable predictive model that the latent variables acquired are stable and robust, as they always learn the same representation regardless of the network initial states. Full Encoder can be used to determine the degrees of freedom in a simple non-linear system and can be useful for data compression or anomaly detection. Full Encoder can also be combined with the beta-VAE framework to sort out the importance of the generative factors, providing more insights for non-linear system analysis. These qualities will make FE useful for analyzing real-life industrial non-linear systems. To validate, we created a toy dataset with a custom-made non-linear system to test it and compare its properties to those of VAE and beta-VAE's.
SA-EMO: Structure-Aligned Encoder Mixture of Operators for Generalizable Full-waveform Inversion
School of Science, China University of Mining and Technology, Beijing（科学学院，中国矿业大学（北京））；School of Artificial Intelligence, China University of Mining and Technology, Beijing（人工智能学院，中国矿业大学（北京））；City University of Hong Kong (Dongguan)（香港城市大学（东莞））
Pay (Cross) Attention to the Melody: Curriculum Masking for Single-Encoder Melodic Harmonization
Department of Music Technology（音乐技术系）；Acoustics Hellenic Mediterranean University, Greece Archimedes, Athena RC, Greece（声学 希腊地中海大学 阿里卡斯萨斯）；Institute of Language（语言研究所）；School of Music Studies Aristotle University of Thessaloniki, Greece（音乐研究学院 阿里斯托芬大学）
Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement
Acoustics Research Institute, Austrian Academy of Sciences（奥地利科学院声学研究所）；Nantes Université（南特大学）；École Centrale Nantes（南特中央理工学院）；University of Vienna（维也纳大学）
Full-resolution Lung Nodule Segmentation from Chest X-ray Images using Residual Encoder-Decoder Networks
University of Technology Sydney（悉尼科技大学）；IBM Australia Limited（IBM澳大利亚有限公司）；University of New England（新英格兰大学）；Universiti Kebangsaan Malaysia（马来西亚国民大学）；Charles Sturt University（查尔斯斯特大学）；Westmead Hospital（韦斯特米德医院）；Cogninet Australia（科尼尼特澳大利亚公司）；University of Southern Queensland（南昆士兰大学）；Data Science Institute, University of Technology Sydney（悉尼科技大学数据科学学院）
