Related papers: Asymmetric Gained Deep Image Compression With Cont…
We propose a compression based continual task learning method that can dynamically grow a neural network. Inspired from the recent model compression techniques, we employ compression-aware training and perform low-rank weight approximations…
Extracting insight from the enormous quantity of data generated from molecular simulations requires the identification of a small number of collective variables whose corresponding low-dimensional free-energy landscape retains the essential…
Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time. However, practical scenarios demand an asymmetric design, where the decoder requires low complexity to…
This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…
Variation Autoencoder (VAE) has become a powerful tool in modeling the non-linear generative process of data from a low-dimensional latent space. Recently, several studies have proposed to use VAE for unsupervised clustering by using…
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data.…
Deep neural networks represent a powerful class of function approximators that can learn to compress and reconstruct images. Existing image compression algorithms based on neural networks learn quantized representations with a constant…
Recent methods for self-supervised learning can be grouped into two paradigms: contrastive and non-contrastive approaches. Their success can largely be attributed to data augmentation pipelines which generate multiple views of a single…
Although deep learning based image compression methods have achieved promising progress these days, the performance of these methods still cannot match the latest compression standard Versatile Video Coding (VVC). Most of the recent…
Machine learning (ML) models trained to detect physical-layer threats on one optical fiber system often fail catastrophically when applied to a different system, due to variations in operating wavelength, fiber properties, and network…
Distributed learning and Edge AI necessitate efficient data processing, low-latency communication, decentralized model training, and stringent data privacy to facilitate real-time intelligence on edge devices while reducing dependency on…
Most learning-based image compression methods lack efficiency for high image quality due to their non-invertible design. The decoding function of the frequently applied compressive autoencoder architecture is only an approximated inverse of…
Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single…
Learning-based image compression was shown to achieve a competitive performance with state-of-the-art transform-based codecs. This motivated the development of new learning-based visual compression standards such as JPEG-AI. Of particular…
The ever-growing volume of data in imaging sciences stemming from the advancements in imaging technologies, necessitates efficient and reliable storage solutions for such large datasets. This study investigates the compression of industrial…
Recent studies have shown that autoencoder-based models can achieve superior performance on anomaly detection tasks due to their excellent ability to fit complex data in an unsupervised manner. In this work, we propose a novel…
Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the…
Sequential recommendation as an emerging topic has attracted increasing attention due to its important practical significance. Models based on deep learning and attention mechanism have achieved good performance in sequential…
Contemporary lossy image and video coding standards rely on transform coding, the process through which pixels are mapped to an alternative representation to facilitate efficient data compression. Despite impressive performance of…
This paper introduces Associative Compression Networks (ACNs), a new framework for variational autoencoding with neural networks. The system differs from existing variational autoencoders (VAEs) in that the prior distribution used to model…