Related papers: The General Single-Dish Data Format: A Retrospecti…

mmWave radars are compact, inexpensive, and durable sensors that are robust to occlusions and work regardless of environmental conditions, such as weather and darkness. However, this comes at the cost of poor angular resolution, especially…

Single-cell RNA sequencing (scRNA-seq) technology has profiled hundreds of millions of human cells across organs, diseases, development and perturbations to date. However, the high-dimensional sparsity, batch effect noise, category…

Current self-supervised learning methods for 3D medical imaging rely on simple pretext formulations and organ- or modality-specific datasets, limiting their generalizability and scalability. We present 3DINO, a cutting-edge SSL method…

We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level…

Recent progress in compressing explicit radiance field representations, particularly 3D Gaussian Splatting, has substantially reduced memory consumption while improving real-time rendering performance. However, existing approaches remain…

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to protect sensitive data during the training of machine learning models, but its privacy guarantee often comes at a large cost of model performance due to the lack…

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of…

Monocular metric depth estimation (MMDE) is a core challenge in computer vision, playing a pivotal role in real-world applications that demand accurate spatial understanding. Although prior works have shown promising zero-shot performance…

Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…

Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials. However, the…

During 2010-2011, the Medicina 32-m dish hosted the 7-feed 18-26.5 GHz receiver built for the Sardinia Radio Telescope, with the goal to perform its commissioning. This opportunity was exploited to carry out a pilot survey at 20 GHz over…

In many modern data sets, High dimension low sample size (HDLSS) data is prevalent in many fields of studies. There has been an increased focus recently on using machine learning and statistical methods to mine valuable information out of…

We introduce a novel framework for metric depth estimation that enhances pretrained diffusion-based monocular depth estimation (DB-MDE) models with stereo vision guidance. While existing DB-MDE methods excel at predicting relative depth,…

In object detection, a well-defined similarity metric can significantly enhance model performance. Currently, the IoU-based similarity metric is the most commonly preferred choice for detectors. However, detectors using IoU as a similarity…

Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods…

The increasing prevalence of diet-related chronic diseases coupled with the ineffectiveness of traditional diet management methods have resulted in a need for novel tools to accurately and automatically assess meals. Recently, computer…

Over the past few years, monocular depth estimation and completion have been paid more and more attention from the computer vision community because of their widespread applications. In this paper, we introduce novel physics…

Divergence measures play a central role and become increasingly essential in deep learning, yet efficient measures for multiple (more than two) distributions are rarely explored. This becomes particularly crucial in areas where the…

Differentially private SGD (DP-SGD) is one of the most popular methods for solving differentially private empirical risk minimization (ERM). Due to its noisy perturbation on each gradient update, the error rate of DP-SGD scales with the…

Progressive dimensionality reduction algorithms allow for visually investigating intermediate results, especially for large data sets. While different algorithms exist that progressively increase the number of data points, we propose an…