GAN Discriminator

GAN discriminators are crucial components of Generative Adversarial Networks (GANs), tasked with distinguishing real data from synthetically generated data, thereby driving the generator to produce increasingly realistic outputs. Current research focuses on improving discriminator architectures, such as employing deeper networks, incorporating pre-trained feature extractors, and utilizing novel loss functions (e.g., consistency losses) to enhance performance and address issues like bias and overfitting, particularly in data-scarce scenarios. These advancements are significant because they improve the quality and diversity of GAN-generated data, impacting diverse applications ranging from image synthesis and anomaly detection to speech enhancement and malware classification.

Papers

February 15, 2024

Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model
Alvin Grissom II, Ryan F. Lei, Matt Gusdorff, Jeova Farias Sales Rocha Neto, Bailey Lin, Ryan Trotter
Generative Adversarial Network Case Study Pre Trained Realistic Face Luminance Consistency GAN Discriminator Recent StyleGAN3 Architecture

December 20, 2023

Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
Tariq Berrada, Jakob Verbeek, Camille Couprie, Karteek Alahari
GAN Model Pre Trained Backbone Generative Image Model Semantic Image Synthesis Unlocking Insight GAN Discriminator

June 1, 2023

Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Are
Siddarth Asokan, Chandra Sekhar Seelamantula
Generative Adversarial Network Higher Order Bi Discriminator GAN Discriminator

March 30, 2023

KD-DLGAN: Data Limited Image Generation via Knowledge Distillation
Kaiwen Cui, Yingchen Yu, Fangneng Zhan, Shengcai Liao, Shijian Lu1, Eric Xing
Generative Adversarial Network Knowledge Distillation Image Generation GAN Discriminator

October 26, 2022

SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks
Vasily Zadorozhnyy, Qiang Ye, Kazuhito Koishida
Generative Adversarial Network Speech Enhancement GAN Training GAN Discriminator Speech Enhancement Task

October 5, 2022

DEGAN: Time Series Anomaly Detection using Generative Adversarial Network Discriminators and Density Estimation
Yueyan Gu, Farrokh Jazizadeh
Generative Adversarial Network Anomaly Detection Density Estimation Time Series Anomaly Detection GAN Discriminator

August 26, 2022

Learning From Positive and Unlabeled Data Using Observer-GAN
Omar Zamzam, Haleh Akrami, Richard Leahy
LeArning Abstract Generative Adversarial Network Unlabeled Data GAN Training Positive Emotional Language GAN Algorithm GAN Discriminator Learning Based Observer

June 8, 2022

Generative Adversarial Networks and Image-Based Malware Classification
Huy Nguyen, Fabio Di Troia, Genya Ishigaki, Mark Stamp
Adversarial Attack Generative Adversarial Network Malware Classification GAN Discriminator

February 16, 2022

Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing
Zhiyan Chen, Burak Kantarci
Generative Adversarial Network Generative Adversarial Adversarial Detection Detection Network State of the Art GAN Mobile Crowdsensing GAN Discriminator

February 2, 2022

Training a Bidirectional GAN-based One-Class Classifier for Network Intrusion Detection
Wen Xu, Julian Jang-Jaccard, Tong Liu, Fariza Sabrina
Generative Adversarial Network Network Intrusion Detection Bidirectional Correspondence One Class Classifier GAN Discriminator

January 24, 2022

Attacks and Defenses for Free-Riders in Multi-Discriminator GAN
Zilong Zhao, Jiyue Huang, Stefanie Roos, Lydia Y. Chen
Generative Adversarial Network GAN Model New Attack GAN Discriminator

December 27, 2021

Depth and Feature Learning are Provably Beneficial for Neural Network Discriminators
Carles Domingo-Enrich
Large Depth Feature Learning Two Layer ReLU Bi Discriminator Layer ReLU Network GAN Discriminator

November 12, 2021

Bi-Discriminator Class-Conditional Tabular GAN
Mohammad Esmaeilpour, Nourhene Chaalia, Adel Abusitta, Francois-Xavier Devailly, Wissem Maazoun, Patrick Cardinal
GAN Model Tabular Datasets Discriminative Reply Bi Discriminator GAN Discriminator

GAN Discriminator

Papers

Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model

Unlocking Pre-trained Image Backbones for Semantic Image Synthesis

Data Interpolants -- That's What Discriminators in Higher-order Gradient-regularized GANs Are

KD-DLGAN: Data Limited Image Generation via Knowledge Distillation

SCP-GAN: Self-Correcting Discriminator Optimization for Training Consistency Preserving Metric GAN on Speech Enhancement Tasks

DEGAN: Time Series Anomaly Detection using Generative Adversarial Network Discriminators and Density Estimation

Learning From Positive and Unlabeled Data Using Observer-GAN

Generative Adversarial Networks and Image-Based Malware Classification

Generative Adversarial Network-Driven Detection of Adversarial Tasks in Mobile Crowdsensing

Training a Bidirectional GAN-based One-Class Classifier for Network Intrusion Detection

Attacks and Defenses for Free-Riders in Multi-Discriminator GAN

Depth and Feature Learning are Provably Beneficial for Neural Network Discriminators

Bi-Discriminator Class-Conditional Tabular GAN