相关论文: Theoretical Framework and Simulation Results for I…

Diffusion models (DM) can gradually learn to remove noise, which have been widely used in artificial intelligence generated content (AIGC) in recent years. The property of DM for removing noise leads us to wonder whether DM can be applied…

Accurate medical image segmentation is often hindered by noisy labels in training data, due to the challenges of annotating medical images. Prior research works addressing noisy labels tend to make class-dependent assumptions, overlooking…

Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an…

We present a detection scheme for diffusing wave spectroscopy (DWS) based on a two cell geometry that allows efficient ensemble averaging. This is achieved by putting a fast rotating diffuser in the optical path between laser and sample. We…

As its availability and generality in online services, implicit feedback is more commonly used in recommender systems. However, implicit feedback usually presents noisy samples in real-world recommendation scenarios (such as misclicks or…

The paper deals with the task of optimal design of Analog to Digital Converters (ADCs). A general ADC is modeled as a causal discrete-time dynamical system with outputs taking values in a finite set, and its performance is defined as the…

Recently, researchers showed that dirty paper coding (DPC) is the optimal transmission strategy for multiple-input multiple-output broadcast channels (MIMO-BC). In this paper, we study how to determine the maximum weighted sum of DPC rates…

This paper presents a fully integrated second-order level-crossing sampling data converter for real-time data compression and feature extraction. Compared with level-sampling ADCs which sample at fixed voltage levels, the proposed circuits…

This paper tackles two key challenges: detecting small, dense, and overlapping objects (a major hurdle in computer vision) and improving the quality of noisy images, especially those encountered in industrial environments. [1, 2]. Our focus…

Multidimensional Scaling (MDS) is a classical technique for embedding data in low dimensions, still in widespread use today. Originally introduced in the 1950's, MDS was not designed with high-dimensional data in mind; while it remains…

The optimisation of the sensitive region of CMOS sensors with complex non-uniform electric fields requires precise simulations, and this can be achieved by a combination of electrostatic field simulations and Monte Carlo methods. This paper…

Coreset selection seeks to choose a subset of crucial training samples for efficient learning. It has gained traction in deep learning, particularly with the surge in training dataset sizes. Sample selection hinges on two main aspects: a…

Score Distillation Sampling (SDS) has emerged as the de facto approach for text-to-content generation in non-image domains. In this paper, we reexamine the SDS process and introduce a straightforward interpretation that demystifies the…

In this paper we explore several approaches for sampling weight vectors in the context of weighted sum scalarisation approaches for solving multi-criteria decision making (MCDM) problems. This established method converts a multi-objective…

Recently, tremendous human-designed and automatically searched neural networks have been applied to image denoising. However, previous works intend to handle all noisy images in a pre-defined static network architecture, which inevitably…

In this paper, we propose the differentiable channel sparsity search (DCSS) for convolutional neural networks. Unlike traditional channel pruning algorithms which require users to manually set prune ratios for each convolutional layer, DCSS…

The compressed sensing (CS) model can represent the signal recovery process of a large number of radar systems. The detection problem of such radar systems has been studied in many pieces of literature through the technology of debiased…

Quadrature compressive sampling (QuadCS) is a newly introduced sub-Nyquist sampling for acquiring inphase and quadrature (I/Q) components of radio-frequency signals. For applications to pulse-Doppler radars, the QuadCS outputs can be…

We develop a novel algorithm for characterizing Deep Sub-Electron Read Noise (DSERN) image sensors. This algorithm is able to simultaneously compute maximum likelihood estimates of quanta exposure, conversion gain, bias, and read noise of…

Class imbalance is a challenging issue in practical classification problems for deep learning models as well as traditional models. Traditionally successful countermeasures such as synthetic over-sampling have had limited success with…