Related papers: Distributed Learning and Inference with Compressed…

The application of machine learning(ML) and genetic programming(GP) to the image compression domain has produced promising results in many cases. The need for compression arises due to the exorbitant size of data shared on the internet.…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset…

Compressed sensing (CS) provides an elegant framework for recovering sparse signals from compressed measurements. For example, CS can exploit the structure of natural images and recover an image from only a few random measurements. CS is…

Robust perception systems are essential for autonomous vehicle safety. To navigate in a complex urban environment, it is necessary precise sensors with reliable data. The task of understanding the surroundings is hard by itself; for…

Training deep neural networks on large datasets containing high-dimensional data requires a large amount of computation. A solution to this problem is data-parallel distributed training, where a model is replicated into several…

Recent works have shown that learned models can achieve significant performance gains, especially in terms of perceptual quality measures, over traditional methods. Hence, the state of the art in image restoration and compression is getting…

Learning-based methods especially with convolutional neural networks (CNN) are continuously showing superior performance in computer vision applications, ranging from image classification to restoration. For image classification, most…

In recent years, with the development of deep neural networks, end-to-end optimized image compression has made significant progress and exceeded the classic methods in terms of rate-distortion performance. However, most learning-based image…

Traditional vision-based autonomous driving systems often face difficulties in navigating complex environments when relying solely on single-image inputs. To overcome this limitation, incorporating temporal data such as past image frames or…

Learning and Artificial Intelligence (ML/AI) techniques have become increasingly prevalent in high performance computing (HPC). However, these methods depend on vast volumes of floating point data for training and validation which need…

Deep learning based image reconstruction methods outperform traditional methods. However, neural networks suffer from a performance drop when applied to images from a different distribution than the training images. For example, a model…

Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data. We develop a latent variable model…

Self-supervised learning has achieved remarkable success in learning visual representations from clean data, yet remains challenging when clean observations are sparse or not available at all. In this paper, we demonstrate that pretrained…

With the increasing popularity of deep learning in image processing, many learned lossless image compression methods have been proposed recently. One group of algorithms that have shown good performance are based on learned pixel-based…

In the current golden age of multimedia, human visualization is no longer the single main target, with the final consumer often being a machine which performs some processing or computer vision tasks. In both cases, deep learning plays a…

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world computing systems do not always provide stable resource…

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional…