相关论文: FFAD: A Novel Metric for Assessing Generated Time …

This work is an update of a previous paper on the same topic published a few years ago. With the dramatic progress in generative modeling, a suite of new quantitative and qualitative techniques to evaluate models has emerged. Although some…

This paper addresses the challenge of overfitting in the learning of dynamical systems by introducing a novel approach for the generation of synthetic data, aimed at enhancing model generalization and robustness in scenarios characterized…

Publicly available diabetic retinopathy (DR) datasets are imbalanced, containing limited numbers of images with DR. This imbalance contributes to overfitting when training machine learning classifiers. The impact of this imbalance is…

Image-to-image translation has been revolutionized with GAN-based methods. However, existing methods lack the ability to preserve the identity of the source domain. As a result, synthesized images can often over-adapt to the reference…

Infrared imagery enables temperature-based scene understanding using passive sensors, particularly under conditions of low visibility where traditional RGB imaging fails. Yet, developing downstream vision models for infrared applications is…

Generating high-fidelity time series data using generative adversarial networks (GANs) remains a challenging task, as it is difficult to capture the temporal dependence of joint probability distributions induced by time-series data. Towards…

Modern deep learning models in computer vision require large datasets of real images, which are difficult to curate and pose privacy and legal concerns, limiting their commercial use. Recent works suggest synthetic data as an alternative,…

Humans have remarkable selective sensitivity to identities -- easily distinguishing between highly similar identities, even across significantly different contexts such as diverse viewpoints or lighting. Vision models have struggled to…

Generative models like Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs) often fail to capture the full diversity of their training data, leading to mode collapse. While this issue is well-explored in image…

Synthetic Time Series Generation (TSG) is crucial in a range of applications, including data augmentation, anomaly detection, and privacy preservation. Although significant strides have been made in this field, existing methods exhibit…

With the rapid advancement of generative AI, synthetic content across images, videos, and audio has become increasingly realistic, amplifying the risk of misinformation. Existing detection approaches predominantly focus on binary…

Medical imaging is an essential tool for diagnosing and treating diseases. However, lacking medical images can lead to inaccurate diagnoses and ineffective treatments. Generative models offer a promising solution for addressing medical…

Deep metric learning aims to learn an embedding space where the distance between data reflects their class equivalence, even when their classes are unseen during training. However, the limited number of classes available in training…

We introduce Score identity Distillation (SiD), an innovative data-free method that distills the generative capabilities of pretrained diffusion models into a single-step generator. SiD not only facilitates an exponentially fast reduction…

Time-series analysis is critical for a diversity of applications in science and engineering. By leveraging the strengths of modern gradient descent algorithms, the Fourier transform, multi-resolution analysis, and Bayesian spectral…

The advances of modern localization techniques and the wide spread of mobile devices have provided us great opportunities to collect and mine human mobility trajectories. In this work, we focus on passively collected trajectories, which are…

Forward gradient descent (FGD) has been proposed as a biologically more plausible alternative of gradient descent as it can be computed without backward pass. Considering the linear model with $d$ parameters, previous work has found that…

In a way similar to the string-to-string correction problem we address time series similarity in the light of a time-series-to-time-series-correction problem for which the similarity between two time series is measured as the minimum cost…

An increasing number of generative music models can be conditioned on an audio prompt that serves as musical context for which the model is to create an accompaniment (often further specified using a text prompt). Evaluation of how well…

Image quality evaluation accurately is vital in developing image stitching algorithms as it directly reflects the algorithms progress. However, commonly used objective indicators always produce inconsistent and even conflicting results with…