IEEE

Dual Discriminator Hybrid Quantum Generative Adversarial Networks for Improved GAN Performance

Abstract: This study presents an investigation of the Dual Discriminator Hybrid Quantum Generative Adversarial Network (DDHQ-GAN), a framework designed to enhance the performance of conventional ...
IEEE

Defending Against Adversarial Attack Through Generative Adversarial Networks

Abstract: Deep neural networks are increasingly used in image processing tasks. However, deep learning models often show vulnerability when facing adversarial attacks. Active defense is an important ...
GitHub

SA-GAN++: Self-Attention DCGAN with CLIP-Enhanced Multimodal Discriminator

Self-Attention Generator (G++): SAGAN-style self-attention block at 16×16 resolution for long-range spatial dependencies CLIP-Enhanced Dual-Head Discriminator (D++): Multimodal discriminator with real ...
GitHub

Non Linear Independent Components Estimation (NICE)

This project implements the models proposed in NICE: Non-linear Independent Components Estimation paper written by Laurent Dinh, David Krueger and Yoshua Bengio. The results of the models can be found ...