Related papers: Sparser2Sparse: Single-shot Sparser-to-Sparse Lear…

Upsampling LiDAR point clouds in autonomous driving scenarios remains a significant challenge due to the inherent sparsity and complex 3D structures of the data. Recent studies have attempted to address this problem by converting the…

Single-sample face recognition is one of the most challenging problems in face recognition. We propose a novel algorithm to address this problem based on a sparse representation based classification (SRC) framework. The new algorithm is…

The prowess that makes few-shot learning desirable in medical image analysis is the efficient use of the support image data, which are labelled to classify or segment new classes, a task that otherwise requires substantially more training…

We present Spartan, a method for training sparse neural network models with a predetermined level of sparsity. Spartan is based on a combination of two techniques: (1) soft top-k masking of low-magnitude parameters via a regularized optimal…

The large communication cost for exchanging gradients between different nodes significantly limits the scalability of distributed training for large-scale learning models. Motivated by this observation, there has been significant recent…

Snapshot compressive imaging (SCI) surges as a novel way of capturing hyperspectral images. It operates an optical encoder to compress the 3D data into a 2D measurement and adopts a software decoder for the signal reconstruction. Recently,…

Spectral image reconstruction is an important task in snapshot compressed imaging. This paper aims to propose a new end-to-end framework with iterative capabilities similar to a deep unfolding network to improve reconstruction accuracy,…

Spatial Transcriptomics enables mapping of gene expression within its native tissue context, but current platforms measure only a limited set of genes due to experimental constraints and excessive costs. To overcome this, computational…

Spatial transcriptomics (ST) has emerged as a powerful technology for bridging histology imaging with gene expression profiling. However, its application has been limited by low throughput and the need for specialized experimental…

Recent advancements in Spatial Transcriptomics (ST) technology have facilitated detailed gene expression analysis within tissue contexts. However, the high costs and methodological limitations of ST necessitate a more robust predictive…

Identifying damage of structural systems is typically characterized as an inverse problem which might be ill-conditioned due to aleatory and epistemic uncertainties induced by measurement noise and modeling error. Sparse representation can…

A wide range of systems exhibit high dimensional incomplete data. Accurate estimation of the missing data is often desired, and is crucial for many downstream analyses. Many state-of-the-art recovery methods involve supervised learning…

The development of single-cell and spatial transcriptomics has revolutionized our capacity to investigate cellular properties, functions, and interactions in both cellular and spatial contexts. However, the analysis of single-cell and…

Recent image classification algorithms, by learning deep features from large-scale datasets, have achieved significantly better results comparing to the classic feature-based approaches. However, there are still various challenges of image…

Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary. Sparse TTS models can improve on dense models via pruning and extra retraining, or…

We study image segmentation in the biological domain, particularly trait segmentation from specimen images (e.g., butterfly wing stripes, beetle elytra). This fine-grained task is crucial for understanding the biology of organisms, but it…

Spatial transcriptomics is an emerging field that enables the identification of functional regions based on the spatial distribution of gene expression. Integrating this functional information present in transcriptomic data with structural…

Spatial transcriptomics aims to connect high-resolution histology images with spatially resolved gene expression. To achieve better performance on downstream tasks such as gene expression prediction, large-scale pre-training is required to…

Ultrasound imaging faces a trade-off between image quality and hardware complexity caused by dense transducers. Sparse arrays are one popular solution to mitigate this challenge. This work proposes an end-to-end optimization framework that…

As deep learning methods continue to improve medical image segmentation performance, data annotation is still a big bottleneck due to the labor-intensive and time-consuming burden on medical experts, especially for 3D images. To…