Related papers: A novel stacked hybrid autoencoder for imputing LI…
Our examination of existing deep generative models (DGMs), including VAEs and GANs, reveals two problems. First, their capability in handling discrete observations and latent codes is unsatisfactory, though there are interesting efforts.…
Increasingly many real world tasks involve data in multiple modalities or views. This has motivated the development of many effective algorithms for learning a common latent space to relate multiple domains. However, most existing…
Existing blind image quality assessment (BIQA) methods are mostly designed in a disposable way and cannot evolve with unseen distortions adaptively, which greatly limits the deployment and application of BIQA models in real-world scenarios.…
In applied machine learning, concept drift, which is either gradual or abrupt changes in data distribution, can significantly reduce model performance. Typical detection methods,such as statistical tests or reconstruction-based models,are…
Wind turbine reliability is critical to the growing renewable energy sector, where early fault detection significantly reduces downtime and maintenance costs. This paper introduces a novel ensemble-based deep learning framework for…
Questing for learned lossy image coding (LIC) with superior compression performance and computation throughput is challenging. The vital factor behind it is how to intelligently explore Adaptive Neighborhood Information Aggregation (ANIA)…
Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a…
We consider an uplink integrated sensing and communications (ISAC) scenario where the detection of data symbols from multiple user equipment (UEs) occurs simultaneously with a three-dimensional (3D) estimation of the environment, extracted…
By listening to gravity in the low frequency band, between 0.1 mHz and 1 Hz, the future space-based gravitational-wave observatory LISA will be able to detect tens of thousands of astrophysical sources from cosmic dawn to the present. The…
We present the discriminative recurrent sparse auto-encoder model, comprising a recurrent encoder of rectified linear units, unrolled for a fixed number of iterations, and connected to two linear decoders that reconstruct the input and…
The Laser Interferometer Space Antenna (LISA) will feature a prominent anisotropic astrophysical stochastic gravitational wave signal, arising from the tens of millions of unresolved mHz white dwarf binaries in the Milky Way: the Galactic…
The integration of hyperspectral imaging (HSI) and LiDAR data within new linear feature spaces offers a promising solution to the challenges posed by the high-dimensionality and redundancy inherent in HSIs. This study introduces a dual…
In this paper, we present list autoencoder (listAE) to mimic list decoding used in classical coding theory. With listAE, the decoder network outputs a list of decoded message word candidates. To train the listAE, a genie is assumed to be…
In the hierarchical paradigm of galaxy formation, central massive black holes (MBHs) are expected to coalesce after the merger of their host galaxies. One of the main goals of the Laser Interferometer Space Antenna (LISA) is to constrain…
Combining neuroimaging datasets from multiple sites and scanners can help increase statistical power and thus provide greater insight into subtle neuroanatomical effects. However, site-specific effects pose a challenge by potentially…
Inferring the intrinsic population of compact binary mergers is complicated by detector selection biases and measurement uncertainties. Traditional parametric methods are limited by the need to presuppose functional forms, introducing…
This work extends our previous study on enhancing 3D LiDAR point-cloud classification with product coefficients \cite{medina2025integratingproductcoefficientsimproved}, measure-theoretic descriptors that complement the original spatial…
Disentangled learning representations have promising utility in many applications, but they currently suffer from serious reliability issues. We present Gaussian Channel Autoencoder (GCAE), a method which achieves reliable disentanglement…
Missing data is a significant problem impacting all domains. State-of-the-art framework for minimizing missing data bias is multiple imputation, for which the choice of an imputation model remains nontrivial. We propose a multiple…
Deep generative models have made tremendous advances in image and signal representation learning and generation. These models employ the full Euclidean space or a bounded subset as the latent space, whose flat geometry, however, is often…