paper-with-me

홈 › Papers

Visually Evaluating Generative Adversarial Networks Using Itself under Multivariate Time Series

2022-08-04 · Qilong Pan

Visually evaluating the goodness of generated Multivariate Time Series (MTS) are difficult to implement, especially in the case that the generative model is Generative Adversarial Networks (GANs). We present a general framework named Gaussian GANs to visually evaluate GANs using itself under the MTS generation task. Firstly, we attempt to find the transformation function in the multivariate Kolmogorov Smirnov (MKS) test by explicitly reconstructing the architecture of GANs. Secondly, we conduct the normality test of transformed MST where the Gaussian GANs serves as the transformation function in the MKS test. In order to simplify the normality test, an efficient visualization is proposed using the chi square distribution. In the experiment, we use the UniMiB dataset and provide empirical evidence showing that the normality test using Gaussian GANs and chi sqaure visualization is effective and credible.

📄 PDF Abstract BibTeX arXiv:2208.02649

Code (1)

jack-pan-ai/GaussianGANs 공식 구현 pytorch

Tasks

Time SeriesTime Series Analysis

Methods 이 논문이 사용한 방법론

Test 설명 없음
MTS 설명 없음

Similar Papers 제목 키워드 기반

High-Fidelity Generative Image Compression

2020-06-17 · NeurIPS 2020 12 · Fabian Mentzer, George Toderici, Michael Tschannen, Eirikur Agustsson

We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system. In particular, we investigate normalization layers, generator …

Image CompressionVocal Bursts Intensity Prediction

DPSRGAN: Dilation Patch Super-Resolution Generative Adversarial Networks

2021-05-10 · 6th International Conference for Convergence in Technology (I2CT) 2021 5 · Kapil Mirchandani, Kushal Chordiya

Single Image Super-Resolution (SISR) has proven itself as a highly challenging and ill-posed problem. Multiple methods have been applied to this problem in the past, with varying degrees of success. Recently, methods usi…

Image Super-ResolutionSuper-Resolution

Bot-Adversarial Dialogue for Safe Conversational Agents

2021-06-01 · NAACL 2021 4 · Jing Xu, Da Ju, Margaret Li, Y-Lan Boureau 외

Conversational agents trained on large unlabeled corpora of human interactions will learn patterns and mimic behaviors therein, which include offensive or otherwise toxic behavior. We introduce a new human-and-model-in-t…

SpotEdit: Evaluating Visually-Guided Image Editing Methods

2025-08-25 · Sara Ghazanfari, Wei-An Lin, Haitong Tian, Ersin Yumer arxiv

Visually-guided image editing, where edits are conditioned on both visual cues and textual prompts, has emerged as a powerful paradigm for fine-grained, controllable content generation. Although recent generative models …

Image Editing

Generative Adversarial Networks Applied for Privacy Preservation in Biometric-Based Authentication and Identification

2025-09-24 · Lubos Mjachky, Ivan Homoliak arxiv

Biometric-based authentication systems are getting broadly adopted in many areas. However, these systems do not allow participating users to influence the way their data is used. Furthermore, the data may leak and can be…