Related papers: Learning to Upsample by Learning to Sample

Previous work on learning physical systems from data has focused on high-resolution grid-structured measurements. However, real-world knowledge of such systems (e.g. weather data) relies on sparsely scattered measuring stations. In this…

The creation of high-fidelity 3D assets is often hindered by a 'pixel-level pain point': the loss of high-frequency details. Existing methods often trade off one aspect for another: either sacrificing cross-view consistency, resulting in…

Deep neural networks (DNNs) frequently contain far more weights, represented at a higher precision, than are required for the specific task which they are trained to perform. Consequently, they can often be compressed using techniques such…

Recently, the computer vision and machine learning community has been in favor of feature extraction pipelines that rely on a coding step followed by a linear classifier, due to their overall simplicity, well understood properties of linear…

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work…

Diffusion Transformers achieve impressive generative quality but remain computationally expensive due to iterative sampling. Recently, dynamic resolution sampling has emerged as a promising acceleration technique by reducing the resolution…

One of the limitations of deep learning models with sparse features today stems from the predefined nature of their input, which requires a dictionary be defined prior to the training. With this paper we propose both a theory and a working…

Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning. In this paper,…

Hyperspectral pansharpening consists of fusing a high-resolution panchromatic band and a low-resolution hyperspectral image to obtain a new image with high resolution in both the spatial and spectral domains. These remote sensing products…

The bootstrap is a widely used procedure for statistical inference because of its simplicity and attractive statistical properties. However, the vanilla version of bootstrap is no longer feasible computationally for many modern massive…

Depthwise separable convolutions are a fundamental component in efficient Deep Neural Networks, as they reduce the number of parameters and operations compared to traditional convolutions while maintaining comparable accuracy. However,…

In an ever expanding set of research and application areas, deep neural networks (DNNs) set the bar for algorithm performance. However, depending upon additional constraints such as processing power and execution time limits, or…

While point-based neural architectures have demonstrated their efficacy, the time-consuming sampler currently prevents them from performing real-time reasoning on scene-level point clouds. Existing methods attempt to overcome this issue by…

Convolutional neural networks (CNNs) have been widely used in efficient image super-resolution. However, for CNN-based methods, performance gains often require deeper networks and larger feature maps, which increase complexity and inference…

This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes. To tackle this challenging issue, we propose a novel end-to-end learning-based…

Recently supervised learning rapidly develops in scene text segmentation. However, the lack of high-quality datasets and the high cost of pixel annotation greatly limit the development of them. Considering the well-performed few-shot…

Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first…

Deep learning is reshaping mobile applications, with a growing trend of deploying deep neural networks (DNNs) directly to mobile and embedded devices to address real-time performance and privacy. To accommodate local resource limitations,…

We present a method for inferring dense depth maps from images and sparse depth measurements by leveraging synthetic data to learn the association of sparse point clouds with dense natural shapes, and using the image as evidence to validate…

We introduce an algorithm that simplifies the construction of efficient estimators, making them accessible to a broader audience. 'Dimple' takes as input computer code representing a parameter of interest and outputs an efficient estimator.…