Related papers: Efficient Summation of Arbitrary Masks -- ESAM
In recommendation systems, users frequently engage in multiple types of behaviors, such as clicking, adding to a cart, and purchasing. However, with diversified behavior data, user behavior sequences will become very long in the short term,…
Sharpness-aware minimization (SAM), which searches for flat minima by min-max optimization, has been shown to be useful in improving model generalization. However, since each SAM update requires computing two gradients, its computational…
Reinforcement learning (RL) has become a key training step for improving mathematical reasoning in large language models (LLMs), but it often has high GPU memory usage, which makes it hard to use in settings with limited resources. To…
Face super-resolution (FSR) is a critical technique for enhancing low-resolution facial images and has significant implications for face-related tasks. However, existing FSR methods are limited by fixed up-sampling scales and sensitivity to…
The Diffusion Entropy algorithm is a method that allows the study of correlated non stationary time series and allows the discrimination between signal and uncorrelated noise. DE provides a quantitative measure of the complexity by means of…
Few-shot classification and segmentation (FS-CS) focuses on jointly performing multi-label classification and multi-class segmentation using few annotated examples. Although the current state of the art (SOTA) achieves high accuracy in both…
The diffusion model has recently emerged as a potent approach in computer vision, demonstrating remarkable performances in the field of generative artificial intelligence. Capable of producing high-quality synthetic images, diffusion models…
Segment Anything Model (SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when directly applied to medical image segmentation, since SAM…
Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to…
Recent feature matching methods have achieved remarkable performance but lack efficiency consideration. In this paper, we revisit the mainstream detector-free matching pipeline and improve all its stages considering both accuracy and…
Sharpness-Aware Minimization (SAM) has emerged as a promising approach for effectively reducing the generalization error. However, SAM incurs twice the computational cost compared to base optimizer (e.g., SGD). We propose Asymptotic…
Fast radio bursts (FRBs), millisecond-duration radio transient events, possess the potential to serve as excellent cosmological probes. The FRB redshift distribution contains information about the FRB sources, providing key constraints on…
Next-generation particle accelerators demand advanced beam-diagnostic capabilities to ensure high performance, operational reliability, and sustainable machine operation. Increasing beam intensities and stored energies make the precise…
Bayesian variable selection methods are powerful techniques for fitting and inferring on sparse high-dimensional linear regression models. However, many are computationally intensive or require restrictive prior distributions on model…
Estimating and disentangling epistemic uncertainty, uncertainty that is reducible with more training data, and aleatoric uncertainty, uncertainty that is inherent to the task at hand, is critically important when applying machine learning…
Scanning transmission electron microscopy (STEM) has a broad range of applications in materials characterization, including real-space imaging, spectroscopy, and diffraction, at length scales from the micron to sub-{\AA}ngstr\"om. The…
Characterising the noise of an airborne electromagnetic (AEM) system is critical in correctly imaging the earth's subsurface conductivity. Deterministic and probabilistic geophysical inversion algorithms require foreknowledge of the system…
We present two efficient numerical methods for susceptibility artifact correction applicable in Echo Planar Imaging (EPI), an ultra fast Magnetic Resonance Imaging (MRI) technique widely used in clinical applications. Both methods address a…
Based on the Denoising Diffusion Probabilistic Model (DDPM), medical image segmentation can be described as a conditional image generation task, which allows to compute pixel-wise uncertainty maps of the segmentation and allows an implicit…
Accurate noise modelling is important for training of deep learning reconstruction algorithms. While noise models are well known for traditional imaging techniques, the noise distribution of a novel sensor may be difficult to determine a…