Related papers: Autoencoder Reconstruction of Cosmological Microle…
Time-delay cosmography can be used to infer the Hubble parameter $H_0$ by measuring the relative time delays between multiple images of gravitationally-lensed quasars. A few of such systems have already been used to measure $H_0$: their…
Image memorability refers to the phenomenon where certain images are more likely to be remembered than others. It is a quantifiable and intrinsic image attribute, defined as the likelihood of an image being remembered upon a single…
We present HEALFormer, a transformer-based neural network architecture for weak gravitational lensing mass mapping that reconstructs convergence maps from incomplete and noisy shear observations on the celestial sphere. The model operates…
Strongly lensed variable quasars can serve as precise cosmological probes, provided that time delays between the image fluxes can be accurately measured. A number of methods have been proposed to address this problem. In this paper, we…
In audio processing applications, the generation of expressive sounds based on high-level representations demonstrates a high demand. These representations can be used to manipulate the timbre and influence the synthesis of creative…
In this paper we develop a new unsupervised machine learning technique comprised of a feature extractor, a convolutional autoencoder (CAE), and a clustering algorithm consisting of a Bayesian Gaussian mixture model (BGM). We apply this…
In this paper, we build autoencoders to learn a latent space from unlabeled image datasets obtained from the Mars rover. Then, once the latent feature space has been learnt, we use k-means to cluster the data. We test the performance of the…
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…
A fundamental aspect of limitations in learning any computation in neural architectures is characterizing their optimal capacities. An important, widely-used neural architecture is known as autoencoders where the network reconstructs the…
Autoencoders are a widespread tool in machine learning to transform high-dimensional data into a lowerdimensional representation which still exhibits the essential characteristics of the input. The encoder provides an embedding from the…
Autoencoders gained popularity in the deep learning revolution given their ability to compress data and provide dimensionality reduction. Although prominent deep learning methods have been used to enhance autoencoders, the need to provide…
Mask-based lensless imagers are smaller and lighter than traditional lensed cameras. In these imagers, the sensor does not directly record an image of the scene; rather, a computational algorithm reconstructs it. Typically, mask-based…
The gravitational field of a galaxy can act as a lens and deflect the light emitted by a more distant object such as a quasar. Strong gravitational lensing causes multiple images of the same quasar to appear in the sky. Since the light in…
Extragalactic foregrounds in temperature maps of the Cosmic Microwave Background (CMB) severely limit the ability of standard estimators to reconstruct the weak lensing potential. These foregrounds are not fully removable by multi-frequency…
All-sky observations of the Milky Way show both Galactic and non-Galactic diffuse emission, for example from interstellar matter or the cosmic microwave background (CMB). The different emitters are partly superimposed in the measurements,…
Autoencoders are commonly trained using element-wise loss. However, element-wise loss disregards high-level structures in the image which can lead to embeddings that disregard them as well. A recent improvement to autoencoders that helps…
Background and Aim: Over-fitting issue has been the reason behind deep learning technology not being successfully implemented in oral cancer images classification. The aims of this research were reducing overfitting for accurately producing…
In quantised autoencoders, images are usually split into local patches, each encoded by one token. This representation is redundant in the sense that the same number of tokens is spend per region, regardless of the visual information…
Autoencoding, which aims to reconstruct the input images through a bottleneck latent representation, is one of the classic feature representation learning strategies. It has been shown effective as an auxiliary task for semi-supervised…
We propose a lossy image compression system using the deep-learning autoencoder structure to participate in the Challenge on Learned Image Compression (CLIC) 2018. Our autoencoder uses the residual blocks with skip connections to reduce the…