中文
相关论文

相关论文: "GAN I hire you?" -- A System for Personalized Vir…

200 篇论文

Generative adversarial networks (GANs) have drawn enormous attention due to the simple yet effective training mechanism and superior image generation quality. With the ability to generate photo-realistic high-resolution (e.g.,…

计算机视觉与模式识别 · 计算机科学 2022-07-22 Ming Liu , Yuxiang Wei , Xiaohe Wu , Wangmeng Zuo , Lei Zhang

Generative adversarial networks (GANs) has gained tremendous popularity lately due to an ability to reinforce quality of its predictive model with generated objects and the quality of the generative model with and supervised feedback. GANs…

计算机视觉与模式识别 · 计算机科学 2017-05-31 Evgeny Zamyatin , Andrey Filchenkov

Workplace learning is used to train employees systematically, e.g., via e-learning or in 1:1 training. However, this is often deemed ineffective and costly. Whereas pure e-learning lacks the possibility of conversational exercise and…

人机交互 · 计算机科学 2024-05-27 Andreas Bucher , Birgit Schenk , Mateusz Dolata , Gerhard Schwabe

The impressive success of Generative Adversarial Networks (GANs) is often overshadowed by the difficulties in their training. Despite the continuous efforts and improvements, there are still open issues regarding their convergence…

机器学习 · 计算机科学 2018-11-08 Yannis Pantazis , Dipjyoti Paul , Michail Fasoulakis , Yannis Stylianou

Emotion recognition is a classic field of research with a typical setup extracting features and feeding them through a classifier for prediction. On the other hand, generative models jointly capture the distributional relationship between…

机器学习 · 计算机科学 2020-11-16 Saurabh Sahu , Rahul Gupta , Carol Espy-Wilson

Generative Adversarial Networks (GAN) have shown great promise in tasks like synthetic image generation, image inpainting, style transfer, and anomaly detection. However, generating discrete data is a challenge. This work presents an…

机器学习 · 计算机科学 2018-04-04 Shreyas Patel , Ashutosh Kakadiya , Maitrey Mehta , Raj Derasari , Rahul Patel , Ratnik Gandhi

Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples with the same (potentially very complex) statistics as the training samples. One major form of training…

无序系统与神经网络 · 物理学 2022-12-12 Steven Durr , Youssef Mroueh , Yuhai Tu , Shenshen Wang

In the context of generating geological facies conditioned on observed data, samples corresponding to all possible conditions are not generally available in the training set and hence the generation of these realizations depends primary on…

机器学习 · 计算机科学 2025-03-25 Alhasan Abdellatif , Ahmed H. Elsheikh , Daniel Busby , Philippe Berthet

Virtual Reality (VR) has emerged as a potential solution for mitigating bias in a job interview by hiding the applicants' demographic features. The current study examines the use of a gender-swapped avatar in a virtual job interview that…

人机交互 · 计算机科学 2024-08-28 Jieun Kim , Hauke Sandhaus , Susan R. Fussell

Generative adversarial networks (GANs) are a class of generative models, known for producing accurate samples. The key feature of GANs is that there are two antagonistic neural networks: the generator and the discriminator. The main…

机器学习 · 计算机科学 2025-08-05 Barbara Franci , Sergio Grammatico

While generative adversarial networks (GANs) have been widely used in research on audio generation, the training of a GAN model is known to be unstable, time consuming, and data inefficient. Among the attempts to ameliorate the training…

声音 · 计算机科学 2022-09-07 Yen-Tung Yeh , Bo-Yu Chen , Yi-Hsuan Yang

Meta Reinforcement Learning (MRL) enables an agent to learn from a limited number of past trajectories and extrapolate to a new task. In this paper, we attempt to improve the robustness of MRL. We build upon model-agnostic meta-learning…

机器学习 · 计算机科学 2021-04-28 Shiqi Chen , Zhengyu Chen , Donglin Wang

A promising approach to improve the robustness and exploration in Reinforcement Learning is collecting human feedback and that way incorporating prior knowledge of the target environment. It is, however, often too expensive to obtain enough…

机器学习 · 计算机科学 2021-11-17 Taku Yamagata , Ryan McConville , Raul Santos-Rodriguez

Generative Adversarial Network (GAN) and its variants have shown promising results in generating synthetic data. However, the issues with GANs are: (i) the learning happens around the training samples and the model often ends up remembering…

计算机视觉与模式识别 · 计算机科学 2020-09-30 Saurabh Gupta , Arun Balaji Buduru , Ponnurangam Kumaraguru

Generative Adversarial Networks (GANs) triggered an increased interest in problem of image generation due to their improved output image quality and versatility for expansion towards new methods. Numerous GAN-based works attempt to improve…

计算机视觉与模式识别 · 计算机科学 2020-10-09 Gulcin Baykal , Gozde Unal

With the recent advances in Reinforcement Learning (RL), there have been tremendous interests in employing RL for recommender systems. However, directly training and evaluating a new RL-based recommendation algorithm needs to collect users'…

信息检索 · 计算机科学 2019-09-11 Xiangyu Zhao , Long Xia , Lixin Zou , Dawei Yin , Jiliang Tang

While Generative Adversarial Networks (GANs) are fundamental to many generative modelling applications, they suffer from numerous issues. In this work, we propose a principled framework to simultaneously mitigate two fundamental issues in…

机器学习 · 计算机科学 2020-11-24 Kwot Sin Lee , Ngoc-Trung Tran , Ngai-Man Cheung

Regression is typically treated as a curve-fitting process where the goal is to fit a prediction function to data. With the help of conditional generative adversarial networks, we propose to solve this age-old problem in a different way; we…

机器学习 · 计算机科学 2024-04-23 Deddy Jobson , Eddy Hudson

Testing new, innovative technologies is a crucial task for safety and acceptance. But how can new systems be tested if no historical real-world data exist? Simulation provides an answer to this important question. Classical simulation tools…

机器学习 · 统计学 2020-09-04 Tom Peetz , Sebastian Vogt , Martin Zaefferer , Thomas Bartz-Beielstein

Despite the recency of their conception, Generative Adversarial Networks (GANs) constitute an extensively researched machine learning sub-field for the creation of synthetic data through deep generative modeling. GANs have consequently been…

网络与互联网体系结构 · 计算机科学 2021-05-11 Hojjat Navidan , Parisa Fard Moshiri , Mohammad Nabati , Reza Shahbazian , Seyed Ali Ghorashi , Vahid Shah-Mansouri , David Windridge